Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2895 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.6531. Min Range: -3.6531

Max Act: 3.6330. Min Act: -0.1700

Data Index: 51268 (Open Web Text)

Max Activating Token Index: 272

Text #1

Max Range: 3.6531. Min Range: -3.6531

Max Act: 3.6211. Min Act: -0.1700

Data Index: 4070257 (Open Web Text)

Max Activating Token Index: 146

Text #2

Max Range: 3.6531. Min Range: -3.6531

Max Act: 3.6531. Min Act: -0.1700

Data Index: 4745930 (Open Web Text)

Max Activating Token Index: 441

Text #3

Max Range: 3.6531. Min Range: -3.6531

Max Act: 3.6056. Min Act: -0.1700

Data Index: 8552224 (Open Web Text)

Max Activating Token Index: 518

Text #4

Max Range: 3.6531. Min Range: -3.6531

Max Act: 3.6115. Min Act: -0.1700

Data Index: 2378441 (Open Web Text)

Max Activating Token Index: 991

Text #5

Max Range: 3.6531. Min Range: -3.6531

Max Act: 3.5912. Min Act: -0.1700

Data Index: 1357620 (Open Web Text)

Max Activating Token Index: 850

Text #6

Max Range: 3.6531. Min Range: -3.6531

Max Act: 3.5757. Min Act: -0.1700

Data Index: 8479635 (Open Web Text)

Max Activating Token Index: 874

Text #7

Max Range: 3.6531. Min Range: -3.6531

Max Act: 3.5759. Min Act: -0.1700

Data Index: 4219239 (Open Web Text)

Max Activating Token Index: 641

Text #8

Max Range: 3.6531. Min Range: -3.6531

Max Act: 3.5624. Min Act: -0.1700

Data Index: 925343 (Open Web Text)

Max Activating Token Index: 115

Text #9

Max Range: 3.6531. Min Range: -3.6531

Max Act: 3.5717. Min Act: -0.1700

Data Index: 6540728 (Open Web Text)

Max Activating Token Index: 236

Text #10

Max Range: 3.6531. Min Range: -3.6531

Max Act: 3.5818. Min Act: -0.1700

Data Index: 7032303 (Open Web Text)

Max Activating Token Index: 385

Text #11

Max Range: 3.6531. Min Range: -3.6531

Max Act: 3.5630. Min Act: -0.1700

Data Index: 7731209 (Open Web Text)

Max Activating Token Index: 565

Text #12

Max Range: 3.6531. Min Range: -3.6531

Max Act: 3.5161. Min Act: -0.1700

Data Index: 6979187 (Open Web Text)

Max Activating Token Index: 438

Text #13

Max Range: 3.6531. Min Range: -3.6531

Max Act: 3.5281. Min Act: -0.1700

Data Index: 1073671 (Open Web Text)

Max Activating Token Index: 784

Text #14

Max Range: 3.6531. Min Range: -3.6531

Max Act: 3.5445. Min Act: -0.1700

Data Index: 395674 (Open Web Text)

Max Activating Token Index: 423

Text #15

Max Range: 3.6531. Min Range: -3.6531

Max Act: 3.5124. Min Act: -0.1700

Data Index: 4416443 (Open Web Text)

Max Activating Token Index: 121

Text #16

Max Range: 3.6531. Min Range: -3.6531

Max Act: 3.5184. Min Act: -0.1700

Data Index: 1922532 (Open Web Text)

Max Activating Token Index: 383

Text #17

Max Range: 3.6531. Min Range: -3.6531

Max Act: 3.5209. Min Act: -0.1700

Data Index: 3578463 (Open Web Text)

Max Activating Token Index: 326

Text #18

Max Range: 3.6531. Min Range: -3.6531

Max Act: 3.4957. Min Act: -0.1700

Data Index: 651014 (Open Web Text)

Max Activating Token Index: 561

Text #19

Max Range: 3.6531. Min Range: -3.6531

Max Act: 3.4810. Min Act: -0.1700

Data Index: 5209125 (Open Web Text)

Max Activating Token Index: 924