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

Dataset: Open Web Text

Neuron 1303 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: 4.5917. Min Range: -4.5917

Max Act: 4.5357. Min Act: -0.1700

Data Index: 3881532 (Open Web Text)

Max Activating Token Index: 796

Text #1

Max Range: 4.5917. Min Range: -4.5917

Max Act: 4.5917. Min Act: -0.1700

Data Index: 6195803 (Open Web Text)

Max Activating Token Index: 525

Text #2

Max Range: 4.5917. Min Range: -4.5917

Max Act: 4.4972. Min Act: -0.1700

Data Index: 8144622 (Open Web Text)

Max Activating Token Index: 887

Text #3

Max Range: 4.5917. Min Range: -4.5917

Max Act: 4.4582. Min Act: -0.1700

Data Index: 7550202 (Open Web Text)

Max Activating Token Index: 560

Text #4

Max Range: 4.5917. Min Range: -4.5917

Max Act: 4.4260. Min Act: -0.1700

Data Index: 2186540 (Open Web Text)

Max Activating Token Index: 294

Text #5

Max Range: 4.5917. Min Range: -4.5917

Max Act: 4.4088. Min Act: -0.1700

Data Index: 6541763 (Open Web Text)

Max Activating Token Index: 298

Text #6

Max Range: 4.5917. Min Range: -4.5917

Max Act: 4.4638. Min Act: -0.1700

Data Index: 7627367 (Open Web Text)

Max Activating Token Index: 398

Text #7

Max Range: 4.5917. Min Range: -4.5917

Max Act: 4.4037. Min Act: -0.1700

Data Index: 1894345 (Open Web Text)

Max Activating Token Index: 987

Text #8

Max Range: 4.5917. Min Range: -4.5917

Max Act: 4.4192. Min Act: -0.1700

Data Index: 6135467 (Open Web Text)

Max Activating Token Index: 1022

Text #9

Max Range: 4.5917. Min Range: -4.5917

Max Act: 4.3828. Min Act: -0.1700

Data Index: 4553138 (Open Web Text)

Max Activating Token Index: 637

Text #10

Max Range: 4.5917. Min Range: -4.5917

Max Act: 4.3998. Min Act: -0.1700

Data Index: 5387911 (Open Web Text)

Max Activating Token Index: 940

Text #11

Max Range: 4.5917. Min Range: -4.5917

Max Act: 4.3543. Min Act: -0.1700

Data Index: 6630999 (Open Web Text)

Max Activating Token Index: 98

Text #12

Max Range: 4.5917. Min Range: -4.5917

Max Act: 4.3480. Min Act: -0.1700

Data Index: 8040424 (Open Web Text)

Max Activating Token Index: 880

Text #13

Max Range: 4.5917. Min Range: -4.5917

Max Act: 4.3385. Min Act: -0.1700

Data Index: 7351803 (Open Web Text)

Max Activating Token Index: 483

Text #14

Max Range: 4.5917. Min Range: -4.5917

Max Act: 4.3374. Min Act: -0.1700

Data Index: 7984874 (Open Web Text)

Max Activating Token Index: 473

Text #15

Max Range: 4.5917. Min Range: -4.5917

Max Act: 4.3554. Min Act: -0.1700

Data Index: 8279192 (Open Web Text)

Max Activating Token Index: 159

Text #16

Max Range: 4.5917. Min Range: -4.5917

Max Act: 4.3295. Min Act: -0.1700

Data Index: 3104069 (Open Web Text)

Max Activating Token Index: 48

Text #17

Max Range: 4.5917. Min Range: -4.5917

Max Act: 4.3322. Min Act: -0.1700

Data Index: 8630596 (Open Web Text)

Max Activating Token Index: 382

Text #18

Max Range: 4.5917. Min Range: -4.5917

Max Act: 4.3827. Min Act: -0.1700

Data Index: 2260979 (Open Web Text)

Max Activating Token Index: 696

Text #19

Max Range: 4.5917. Min Range: -4.5917

Max Act: 4.3155. Min Act: -0.1700

Data Index: 3306062 (Open Web Text)

Max Activating Token Index: 891