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

Dataset: Open Web Text

Neuron 1315 in Layer 5

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: 4.7186. Min Range: -4.7186

Max Act: 4.7186. Min Act: -0.1700

Data Index: 3836250 (Open Web Text)

Max Activating Token Index: 855

Text #1

Max Range: 4.7186. Min Range: -4.7186

Max Act: 4.5967. Min Act: -0.1700

Data Index: 7331248 (Open Web Text)

Max Activating Token Index: 907

Text #2

Max Range: 4.7186. Min Range: -4.7186

Max Act: 4.5351. Min Act: -0.1700

Data Index: 1999039 (Open Web Text)

Max Activating Token Index: 863

Text #3

Max Range: 4.7186. Min Range: -4.7186

Max Act: 4.5014. Min Act: -0.1700

Data Index: 2159056 (Open Web Text)

Max Activating Token Index: 137

Text #4

Max Range: 4.7186. Min Range: -4.7186

Max Act: 4.4860. Min Act: -0.1700

Data Index: 4007530 (Open Web Text)

Max Activating Token Index: 923

Text #5

Max Range: 4.7186. Min Range: -4.7186

Max Act: 4.3924. Min Act: -0.1700

Data Index: 5425078 (Open Web Text)

Max Activating Token Index: 598

Text #6

Max Range: 4.7186. Min Range: -4.7186

Max Act: 4.4224. Min Act: -0.1700

Data Index: 3109998 (Open Web Text)

Max Activating Token Index: 362

Text #7

Max Range: 4.7186. Min Range: -4.7186

Max Act: 4.4336. Min Act: -0.1700

Data Index: 1090734 (Open Web Text)

Max Activating Token Index: 778

Text #8

Max Range: 4.7186. Min Range: -4.7186

Max Act: 4.4512. Min Act: -0.1700

Data Index: 2192530 (Open Web Text)

Max Activating Token Index: 771

Text #9

Max Range: 4.7186. Min Range: -4.7186

Max Act: 4.4048. Min Act: -0.1700

Data Index: 4773118 (Open Web Text)

Max Activating Token Index: 490

Text #10

Max Range: 4.7186. Min Range: -4.7186

Max Act: 4.4465. Min Act: -0.1700

Data Index: 3337427 (Open Web Text)

Max Activating Token Index: 313

Text #11

Max Range: 4.7186. Min Range: -4.7186

Max Act: 4.3973. Min Act: -0.1700

Data Index: 8685773 (Open Web Text)

Max Activating Token Index: 864

Text #12

Max Range: 4.7186. Min Range: -4.7186

Max Act: 4.4148. Min Act: -0.1700

Data Index: 7045927 (Open Web Text)

Max Activating Token Index: 563

Text #13

Max Range: 4.7186. Min Range: -4.7186

Max Act: 4.3860. Min Act: -0.1700

Data Index: 455469 (Open Web Text)

Max Activating Token Index: 180

Text #14

Max Range: 4.7186. Min Range: -4.7186

Max Act: 4.3811. Min Act: -0.1700

Data Index: 4736452 (Open Web Text)

Max Activating Token Index: 1009

Text #15

Max Range: 4.7186. Min Range: -4.7186

Max Act: 4.3789. Min Act: -0.1700

Data Index: 4494014 (Open Web Text)

Max Activating Token Index: 581

Text #16

Max Range: 4.7186. Min Range: -4.7186

Max Act: 4.3541. Min Act: -0.1700

Data Index: 5007897 (Open Web Text)

Max Activating Token Index: 539

Text #17

Max Range: 4.7186. Min Range: -4.7186

Max Act: 4.3614. Min Act: -0.1700

Data Index: 7334893 (Open Web Text)

Max Activating Token Index: 230

Text #18

Max Range: 4.7186. Min Range: -4.7186

Max Act: 4.3470. Min Act: -0.1700

Data Index: 987267 (Open Web Text)

Max Activating Token Index: 139

Text #19

Max Range: 4.7186. Min Range: -4.7186

Max Act: 4.3306. Min Act: -0.1700

Data Index: 7250087 (Open Web Text)

Max Activating Token Index: 851