< Prev | Home | Model | Random | Next >

Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer

Dataset: Open Web Text

Neuron 48 in Layer 35

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')



Text #0

Max Range: 10.6526. Min Range: -10.6526

Max Act: 10.6526. Min Act: -0.1700

Data Index: 728945 (Open Web Text)

Max Activating Token Index: 616

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 10.6526. Min Range: -10.6526

Max Act: 10.4026. Min Act: -0.1700

Data Index: 207052 (Open Web Text)

Max Activating Token Index: 68

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 10.6526. Min Range: -10.6526

Max Act: 10.2776. Min Act: -0.1700

Data Index: 4254680 (Open Web Text)

Max Activating Token Index: 941

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 10.6526. Min Range: -10.6526

Max Act: 10.2776. Min Act: -0.1700

Data Index: 3051623 (Open Web Text)

Max Activating Token Index: 342

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 10.6526. Min Range: -10.6526

Max Act: 10.2151. Min Act: -0.1700

Data Index: 7087519 (Open Web Text)

Max Activating Token Index: 133

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 10.6526. Min Range: -10.6526

Max Act: 10.2151. Min Act: -0.1700

Data Index: 4139764 (Open Web Text)

Max Activating Token Index: 933

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 10.6526. Min Range: -10.6526

Max Act: 10.2151. Min Act: -0.1700

Data Index: 709532 (Open Web Text)

Max Activating Token Index: 890

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 10.6526. Min Range: -10.6526

Max Act: 10.2151. Min Act: -0.1700

Data Index: 795886 (Open Web Text)

Max Activating Token Index: 507

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 10.6526. Min Range: -10.6526

Max Act: 10.1526. Min Act: -0.1700

Data Index: 3051621 (Open Web Text)

Max Activating Token Index: 718

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 10.6526. Min Range: -10.6526

Max Act: 10.1526. Min Act: -0.1700

Data Index: 5676277 (Open Web Text)

Max Activating Token Index: 353

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 10.6526. Min Range: -10.6526

Max Act: 10.1526. Min Act: -0.1700

Data Index: 8691246 (Open Web Text)

Max Activating Token Index: 784

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 10.6526. Min Range: -10.6526

Max Act: 10.0901. Min Act: -0.1700

Data Index: 1191045 (Open Web Text)

Max Activating Token Index: 526

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 10.6526. Min Range: -10.6526

Max Act: 9.9651. Min Act: -0.1700

Data Index: 2248222 (Open Web Text)

Max Activating Token Index: 345

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 10.6526. Min Range: -10.6526

Max Act: 10.0276. Min Act: -0.1700

Data Index: 3051620 (Open Web Text)

Max Activating Token Index: 859

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 10.6526. Min Range: -10.6526

Max Act: 10.0276. Min Act: -0.1700

Data Index: 1668876 (Open Web Text)

Max Activating Token Index: 743

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 10.6526. Min Range: -10.6526

Max Act: 9.9651. Min Act: -0.1700

Data Index: 5139998 (Open Web Text)

Max Activating Token Index: 493

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 10.6526. Min Range: -10.6526

Max Act: 10.0276. Min Act: -0.1700

Data Index: 2248221 (Open Web Text)

Max Activating Token Index: 189

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 10.6526. Min Range: -10.6526

Max Act: 9.9026. Min Act: -0.1700

Data Index: 5139996 (Open Web Text)

Max Activating Token Index: 583

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 10.6526. Min Range: -10.6526

Max Act: 9.9651. Min Act: -0.1700

Data Index: 713681 (Open Web Text)

Max Activating Token Index: 902

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 10.6526. Min Range: -10.6526

Max Act: 9.9026. Min Act: -0.1700

Data Index: 6609439 (Open Web Text)

Max Activating Token Index: 981

Click toggle to see full text

Truncated

Full Text #19