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

Dataset: Open Web Text

Neuron 912 in Layer 6

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: 3.5082. Min Range: -3.5082

Max Act: 3.5082. Min Act: -0.1700

Data Index: 931477 (Open Web Text)

Max Activating Token Index: 159

Text #1

Max Range: 3.5082. Min Range: -3.5082

Max Act: 3.4853. Min Act: -0.1700

Data Index: 8015095 (Open Web Text)

Max Activating Token Index: 101

Text #2

Max Range: 3.5082. Min Range: -3.5082

Max Act: 3.4785. Min Act: -0.1700

Data Index: 4880794 (Open Web Text)

Max Activating Token Index: 802

Text #3

Max Range: 3.5082. Min Range: -3.5082

Max Act: 3.4044. Min Act: -0.1700

Data Index: 4178592 (Open Web Text)

Max Activating Token Index: 647

Text #4

Max Range: 3.5082. Min Range: -3.5082

Max Act: 3.3903. Min Act: -0.1700

Data Index: 6995308 (Open Web Text)

Max Activating Token Index: 559

Text #5

Max Range: 3.5082. Min Range: -3.5082

Max Act: 3.3866. Min Act: -0.1700

Data Index: 4693359 (Open Web Text)

Max Activating Token Index: 945

Text #6

Max Range: 3.5082. Min Range: -3.5082

Max Act: 3.3885. Min Act: -0.1700

Data Index: 4068465 (Open Web Text)

Max Activating Token Index: 930

Text #7

Max Range: 3.5082. Min Range: -3.5082

Max Act: 3.4019. Min Act: -0.1700

Data Index: 7968931 (Open Web Text)

Max Activating Token Index: 640

Text #8

Max Range: 3.5082. Min Range: -3.5082

Max Act: 3.3761. Min Act: -0.1700

Data Index: 5008338 (Open Web Text)

Max Activating Token Index: 613

Text #9

Max Range: 3.5082. Min Range: -3.5082

Max Act: 3.3854. Min Act: -0.1700

Data Index: 3103144 (Open Web Text)

Max Activating Token Index: 359

Text #10

Max Range: 3.5082. Min Range: -3.5082

Max Act: 3.3736. Min Act: -0.1700

Data Index: 4406647 (Open Web Text)

Max Activating Token Index: 702

Text #11

Max Range: 3.5082. Min Range: -3.5082

Max Act: 3.3357. Min Act: -0.1700

Data Index: 8585318 (Open Web Text)

Max Activating Token Index: 537

Text #12

Max Range: 3.5082. Min Range: -3.5082

Max Act: 3.3300. Min Act: -0.1700

Data Index: 7459909 (Open Web Text)

Max Activating Token Index: 692

Text #13

Max Range: 3.5082. Min Range: -3.5082

Max Act: 3.3304. Min Act: -0.1700

Data Index: 2057637 (Open Web Text)

Max Activating Token Index: 376

Text #14

Max Range: 3.5082. Min Range: -3.5082

Max Act: 3.3451. Min Act: -0.1700

Data Index: 691841 (Open Web Text)

Max Activating Token Index: 554

Text #15

Max Range: 3.5082. Min Range: -3.5082

Max Act: 3.3139. Min Act: -0.1700

Data Index: 4245300 (Open Web Text)

Max Activating Token Index: 608

Text #16

Max Range: 3.5082. Min Range: -3.5082

Max Act: 3.3155. Min Act: -0.1700

Data Index: 5648241 (Open Web Text)

Max Activating Token Index: 471

Text #17

Max Range: 3.5082. Min Range: -3.5082

Max Act: 3.3045. Min Act: -0.1700

Data Index: 7090323 (Open Web Text)

Max Activating Token Index: 159

Text #18

Max Range: 3.5082. Min Range: -3.5082

Max Act: 3.2930. Min Act: -0.1700

Data Index: 7538452 (Open Web Text)

Max Activating Token Index: 514

Text #19

Max Range: 3.5082. Min Range: -3.5082

Max Act: 3.3215. Min Act: -0.1700

Data Index: 1759879 (Open Web Text)

Max Activating Token Index: 97