< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 32 in Layer 13

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 2.9549. Min Range: -2.9549

Max Act: 2.9549. Min Act: -0.1700

Data Index: 6677632 (Open Web Text)

Max Activating Token Index: 329

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.9549. Min Range: -2.9549

Max Act: 2.9549. Min Act: -0.1700

Data Index: 5918770 (Open Web Text)

Max Activating Token Index: 637

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.9549. Min Range: -2.9549

Max Act: 2.8756. Min Act: -0.1700

Data Index: 133471 (Open Web Text)

Max Activating Token Index: 9

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.9549. Min Range: -2.9549

Max Act: 2.8439. Min Act: -0.1700

Data Index: 5815792 (Open Web Text)

Max Activating Token Index: 77

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.9549. Min Range: -2.9549

Max Act: 2.8121. Min Act: -0.1700

Data Index: 648767 (Open Web Text)

Max Activating Token Index: 361

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.9549. Min Range: -2.9549

Max Act: 2.8280. Min Act: -0.1700

Data Index: 5697781 (Open Web Text)

Max Activating Token Index: 384

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.9549. Min Range: -2.9549

Max Act: 2.7802. Min Act: -0.1700

Data Index: 1027088 (Open Web Text)

Max Activating Token Index: 453

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.9549. Min Range: -2.9549

Max Act: 2.7961. Min Act: -0.1700

Data Index: 4535863 (Open Web Text)

Max Activating Token Index: 525

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.9549. Min Range: -2.9549

Max Act: 2.7802. Min Act: -0.1700

Data Index: 7480751 (Open Web Text)

Max Activating Token Index: 919

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.9549. Min Range: -2.9549

Max Act: 2.7802. Min Act: -0.1700

Data Index: 5485495 (Open Web Text)

Max Activating Token Index: 172

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.9549. Min Range: -2.9549

Max Act: 2.7802. Min Act: -0.1700

Data Index: 6410987 (Open Web Text)

Max Activating Token Index: 192

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.9549. Min Range: -2.9549

Max Act: 2.7643. Min Act: -0.1700

Data Index: 4186316 (Open Web Text)

Max Activating Token Index: 311

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.9549. Min Range: -2.9549

Max Act: 2.7802. Min Act: -0.1700

Data Index: 8334613 (Open Web Text)

Max Activating Token Index: 837

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.9549. Min Range: -2.9549

Max Act: 2.7643. Min Act: -0.1700

Data Index: 12141 (Open Web Text)

Max Activating Token Index: 556

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.9549. Min Range: -2.9549

Max Act: 2.7643. Min Act: -0.1700

Data Index: 5054999 (Open Web Text)

Max Activating Token Index: 480

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.9549. Min Range: -2.9549

Max Act: 2.7643. Min Act: -0.1700

Data Index: 8591733 (Open Web Text)

Max Activating Token Index: 207

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.9549. Min Range: -2.9549

Max Act: 2.7643. Min Act: -0.1700

Data Index: 6224363 (Open Web Text)

Max Activating Token Index: 815

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.9549. Min Range: -2.9549

Max Act: 2.7643. Min Act: -0.1700

Data Index: 2556273 (Open Web Text)

Max Activating Token Index: 591

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.9549. Min Range: -2.9549

Max Act: 2.7483. Min Act: -0.1700

Data Index: 233116 (Open Web Text)

Max Activating Token Index: 626

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.9549. Min Range: -2.9549

Max Act: 2.7483. Min Act: -0.1700

Data Index: 4375944 (Open Web Text)

Max Activating Token Index: 234

Click toggle to see full text

Truncated

Full Text #19