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

Dataset: Open Web Text

Neuron 1221 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: 3.8692. Min Range: -3.8692

Max Act: 3.8692. Min Act: -0.1700

Data Index: 5600279 (Open Web Text)

Max Activating Token Index: 414

Text #1

Max Range: 3.8692. Min Range: -3.8692

Max Act: 3.8519. Min Act: -0.1700

Data Index: 2240166 (Open Web Text)

Max Activating Token Index: 129

Text #2

Max Range: 3.8692. Min Range: -3.8692

Max Act: 3.8292. Min Act: -0.1700

Data Index: 1609176 (Open Web Text)

Max Activating Token Index: 669

Text #3

Max Range: 3.8692. Min Range: -3.8692

Max Act: 3.8311. Min Act: -0.1700

Data Index: 2102605 (Open Web Text)

Max Activating Token Index: 349

Text #4

Max Range: 3.8692. Min Range: -3.8692

Max Act: 3.8164. Min Act: -0.1700

Data Index: 8702524 (Open Web Text)

Max Activating Token Index: 540

Text #5

Max Range: 3.8692. Min Range: -3.8692

Max Act: 3.8083. Min Act: -0.1700

Data Index: 727441 (Open Web Text)

Max Activating Token Index: 389

Text #6

Max Range: 3.8692. Min Range: -3.8692

Max Act: 3.7887. Min Act: -0.1700

Data Index: 1135684 (Open Web Text)

Max Activating Token Index: 572

Text #7

Max Range: 3.8692. Min Range: -3.8692

Max Act: 3.7497. Min Act: -0.1700

Data Index: 7842003 (Open Web Text)

Max Activating Token Index: 891

Text #8

Max Range: 3.8692. Min Range: -3.8692

Max Act: 3.7537. Min Act: -0.1700

Data Index: 4873515 (Open Web Text)

Max Activating Token Index: 782

Text #9

Max Range: 3.8692. Min Range: -3.8692

Max Act: 3.7486. Min Act: -0.1700

Data Index: 4649712 (Open Web Text)

Max Activating Token Index: 707

Text #10

Max Range: 3.8692. Min Range: -3.8692

Max Act: 3.7269. Min Act: -0.1700

Data Index: 2445073 (Open Web Text)

Max Activating Token Index: 930

Text #11

Max Range: 3.8692. Min Range: -3.8692

Max Act: 3.7320. Min Act: -0.1700

Data Index: 748479 (Open Web Text)

Max Activating Token Index: 1001

Text #12

Max Range: 3.8692. Min Range: -3.8692

Max Act: 3.7233. Min Act: -0.1700

Data Index: 7195190 (Open Web Text)

Max Activating Token Index: 946

Text #13

Max Range: 3.8692. Min Range: -3.8692

Max Act: 3.7331. Min Act: -0.1700

Data Index: 8656396 (Open Web Text)

Max Activating Token Index: 755

Text #14

Max Range: 3.8692. Min Range: -3.8692

Max Act: 3.7340. Min Act: -0.1700

Data Index: 1403605 (Open Web Text)

Max Activating Token Index: 637

Text #15

Max Range: 3.8692. Min Range: -3.8692

Max Act: 3.7071. Min Act: -0.1700

Data Index: 2422377 (Open Web Text)

Max Activating Token Index: 677

Text #16

Max Range: 3.8692. Min Range: -3.8692

Max Act: 3.7356. Min Act: -0.1700

Data Index: 1784281 (Open Web Text)

Max Activating Token Index: 1008

Text #17

Max Range: 3.8692. Min Range: -3.8692

Max Act: 3.7271. Min Act: -0.1700

Data Index: 1784289 (Open Web Text)

Max Activating Token Index: 124

Text #18

Max Range: 3.8692. Min Range: -3.8692

Max Act: 3.7302. Min Act: -0.1700

Data Index: 1242406 (Open Web Text)

Max Activating Token Index: 464

Text #19

Max Range: 3.8692. Min Range: -3.8692

Max Act: 3.7235. Min Act: -0.1700

Data Index: 2115470 (Open Web Text)

Max Activating Token Index: 612