< Prev | Home | Model | Random | Next >

Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 44 in Layer 43

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 8.0449. Min Range: -8.0449

Max Act: 8.0449. Min Act: -0.1700

Data Index: 1293271 (Open Web Text)

Max Activating Token Index: 836

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 8.0449. Min Range: -8.0449

Max Act: 7.8886. Min Act: -0.1700

Data Index: 8061634 (Open Web Text)

Max Activating Token Index: 528

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 8.0449. Min Range: -8.0449

Max Act: 7.7324. Min Act: -0.1700

Data Index: 6526615 (Open Web Text)

Max Activating Token Index: 115

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 8.0449. Min Range: -8.0449

Max Act: 7.7324. Min Act: -0.1700

Data Index: 562636 (Open Web Text)

Max Activating Token Index: 529

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 8.0449. Min Range: -8.0449

Max Act: 7.5136. Min Act: -0.1700

Data Index: 507204 (Open Web Text)

Max Activating Token Index: 1012

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 8.0449. Min Range: -8.0449

Max Act: 7.4824. Min Act: -0.1700

Data Index: 5111390 (Open Web Text)

Max Activating Token Index: 114

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 8.0449. Min Range: -8.0449

Max Act: 7.4824. Min Act: -0.1700

Data Index: 3045943 (Open Web Text)

Max Activating Token Index: 383

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 8.0449. Min Range: -8.0449

Max Act: 7.4199. Min Act: -0.1700

Data Index: 4067000 (Open Web Text)

Max Activating Token Index: 671

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 8.0449. Min Range: -8.0449

Max Act: 7.4199. Min Act: -0.1700

Data Index: 3677421 (Open Web Text)

Max Activating Token Index: 413

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 8.0449. Min Range: -8.0449

Max Act: 7.4199. Min Act: -0.1700

Data Index: 6155147 (Open Web Text)

Max Activating Token Index: 824

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 8.0449. Min Range: -8.0449

Max Act: 7.3886. Min Act: -0.1700

Data Index: 3351997 (Open Web Text)

Max Activating Token Index: 407

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 8.0449. Min Range: -8.0449

Max Act: 7.4199. Min Act: -0.1700

Data Index: 4886292 (Open Web Text)

Max Activating Token Index: 182

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 8.0449. Min Range: -8.0449

Max Act: 7.3886. Min Act: -0.1700

Data Index: 4165396 (Open Web Text)

Max Activating Token Index: 123

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 8.0449. Min Range: -8.0449

Max Act: 7.3886. Min Act: -0.1700

Data Index: 8795985 (Open Web Text)

Max Activating Token Index: 523

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 8.0449. Min Range: -8.0449

Max Act: 7.3574. Min Act: -0.1700

Data Index: 6757385 (Open Web Text)

Max Activating Token Index: 633

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 8.0449. Min Range: -8.0449

Max Act: 7.3261. Min Act: -0.1700

Data Index: 2319776 (Open Web Text)

Max Activating Token Index: 771

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 8.0449. Min Range: -8.0449

Max Act: 7.2949. Min Act: -0.1700

Data Index: 5989958 (Open Web Text)

Max Activating Token Index: 988

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 8.0449. Min Range: -8.0449

Max Act: 7.2949. Min Act: -0.1700

Data Index: 7563536 (Open Web Text)

Max Activating Token Index: 178

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 8.0449. Min Range: -8.0449

Max Act: 7.2636. Min Act: -0.1700

Data Index: 4906178 (Open Web Text)

Max Activating Token Index: 1011

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 8.0449. Min Range: -8.0449

Max Act: 7.2636. Min Act: -0.1700

Data Index: 7927086 (Open Web Text)

Max Activating Token Index: 803

Click toggle to see full text

Truncated

Full Text #19