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

Dataset: Open Web Text

Neuron 210 in Layer 1

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: 1.8135. Min Range: -1.8135

Max Act: 1.8124. Min Act: -0.1700

Data Index: 4640267 (Open Web Text)

Max Activating Token Index: 359

Text #1

Max Range: 1.8135. Min Range: -1.8135

Max Act: 1.8135. Min Act: -0.1700

Data Index: 4557123 (Open Web Text)

Max Activating Token Index: 608

Text #2

Max Range: 1.8135. Min Range: -1.8135

Max Act: 1.7849. Min Act: -0.1700

Data Index: 170481 (Open Web Text)

Max Activating Token Index: 1022

Text #3

Max Range: 1.8135. Min Range: -1.8135

Max Act: 1.8054. Min Act: -0.1700

Data Index: 1471575 (Open Web Text)

Max Activating Token Index: 458

Text #4

Max Range: 1.8135. Min Range: -1.8135

Max Act: 1.7445. Min Act: -0.1700

Data Index: 5001656 (Open Web Text)

Max Activating Token Index: 164

Text #5

Max Range: 1.8135. Min Range: -1.8135

Max Act: 1.7381. Min Act: -0.1700

Data Index: 1465189 (Open Web Text)

Max Activating Token Index: 983

Text #6

Max Range: 1.8135. Min Range: -1.8135

Max Act: 1.7427. Min Act: -0.1700

Data Index: 702663 (Open Web Text)

Max Activating Token Index: 562

Text #7

Max Range: 1.8135. Min Range: -1.8135

Max Act: 1.7169. Min Act: -0.1700

Data Index: 5384995 (Open Web Text)

Max Activating Token Index: 672

Text #8

Max Range: 1.8135. Min Range: -1.8135

Max Act: 1.7086. Min Act: -0.1700

Data Index: 3955649 (Open Web Text)

Max Activating Token Index: 584

Text #9

Max Range: 1.8135. Min Range: -1.8135

Max Act: 1.7134. Min Act: -0.1700

Data Index: 809938 (Open Web Text)

Max Activating Token Index: 929

Text #10

Max Range: 1.8135. Min Range: -1.8135

Max Act: 1.7019. Min Act: -0.1700

Data Index: 939602 (Open Web Text)

Max Activating Token Index: 259

Text #11

Max Range: 1.8135. Min Range: -1.8135

Max Act: 1.7104. Min Act: -0.1700

Data Index: 4344426 (Open Web Text)

Max Activating Token Index: 591

Text #12

Max Range: 1.8135. Min Range: -1.8135

Max Act: 1.6925. Min Act: -0.1700

Data Index: 8699157 (Open Web Text)

Max Activating Token Index: 1011

Text #13

Max Range: 1.8135. Min Range: -1.8135

Max Act: 1.6974. Min Act: -0.1700

Data Index: 8553348 (Open Web Text)

Max Activating Token Index: 515

Text #14

Max Range: 1.8135. Min Range: -1.8135

Max Act: 1.6912. Min Act: -0.1700

Data Index: 8631031 (Open Web Text)

Max Activating Token Index: 256

Text #15

Max Range: 1.8135. Min Range: -1.8135

Max Act: 1.6881. Min Act: -0.1700

Data Index: 6397883 (Open Web Text)

Max Activating Token Index: 900

Text #16

Max Range: 1.8135. Min Range: -1.8135

Max Act: 1.6886. Min Act: -0.1700

Data Index: 3338390 (Open Web Text)

Max Activating Token Index: 570

Text #17

Max Range: 1.8135. Min Range: -1.8135

Max Act: 1.6825. Min Act: -0.1700

Data Index: 3414291 (Open Web Text)

Max Activating Token Index: 173

Text #18

Max Range: 1.8135. Min Range: -1.8135

Max Act: 1.6827. Min Act: -0.1700

Data Index: 679095 (Open Web Text)

Max Activating Token Index: 744

Text #19

Max Range: 1.8135. Min Range: -1.8135

Max Act: 1.6794. Min Act: -0.1700

Data Index: 4207116 (Open Web Text)

Max Activating Token Index: 726