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

Dataset: Open Web Text

Neuron 1906 in Layer 4

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: 4.8204. Min Range: -4.8204

Max Act: 4.8204. Min Act: -0.1700

Data Index: 2094746 (Open Web Text)

Max Activating Token Index: 840

Text #1

Max Range: 4.8204. Min Range: -4.8204

Max Act: 4.7465. Min Act: -0.1700

Data Index: 8681627 (Open Web Text)

Max Activating Token Index: 140

Text #2

Max Range: 4.8204. Min Range: -4.8204

Max Act: 4.7448. Min Act: -0.1700

Data Index: 5101539 (Open Web Text)

Max Activating Token Index: 364

Text #3

Max Range: 4.8204. Min Range: -4.8204

Max Act: 4.7554. Min Act: -0.1700

Data Index: 2992796 (Open Web Text)

Max Activating Token Index: 28

Text #4

Max Range: 4.8204. Min Range: -4.8204

Max Act: 4.7584. Min Act: -0.1700

Data Index: 1859510 (Open Web Text)

Max Activating Token Index: 452

Text #5

Max Range: 4.8204. Min Range: -4.8204

Max Act: 4.7658. Min Act: -0.1700

Data Index: 2708328 (Open Web Text)

Max Activating Token Index: 981

Text #6

Max Range: 4.8204. Min Range: -4.8204

Max Act: 4.7543. Min Act: -0.1700

Data Index: 2627014 (Open Web Text)

Max Activating Token Index: 81

Text #7

Max Range: 4.8204. Min Range: -4.8204

Max Act: 4.7441. Min Act: -0.1700

Data Index: 663700 (Open Web Text)

Max Activating Token Index: 289

Text #8

Max Range: 4.8204. Min Range: -4.8204

Max Act: 4.7381. Min Act: -0.1700

Data Index: 470971 (Open Web Text)

Max Activating Token Index: 850

Text #9

Max Range: 4.8204. Min Range: -4.8204

Max Act: 4.7147. Min Act: -0.1700

Data Index: 5574322 (Open Web Text)

Max Activating Token Index: 367

Text #10

Max Range: 4.8204. Min Range: -4.8204

Max Act: 4.7179. Min Act: -0.1700

Data Index: 5034443 (Open Web Text)

Max Activating Token Index: 360

Text #11

Max Range: 4.8204. Min Range: -4.8204

Max Act: 4.7346. Min Act: -0.1700

Data Index: 5593565 (Open Web Text)

Max Activating Token Index: 890

Text #12

Max Range: 4.8204. Min Range: -4.8204

Max Act: 4.7005. Min Act: -0.1700

Data Index: 3777620 (Open Web Text)

Max Activating Token Index: 894

Text #13

Max Range: 4.8204. Min Range: -4.8204

Max Act: 4.7085. Min Act: -0.1700

Data Index: 273025 (Open Web Text)

Max Activating Token Index: 942

Text #14

Max Range: 4.8204. Min Range: -4.8204

Max Act: 4.7286. Min Act: -0.1700

Data Index: 5767199 (Open Web Text)

Max Activating Token Index: 952

Text #15

Max Range: 4.8204. Min Range: -4.8204

Max Act: 4.7082. Min Act: -0.1700

Data Index: 2558886 (Open Web Text)

Max Activating Token Index: 557

Text #16

Max Range: 4.8204. Min Range: -4.8204

Max Act: 4.7430. Min Act: -0.1700

Data Index: 1049009 (Open Web Text)

Max Activating Token Index: 413

Text #17

Max Range: 4.8204. Min Range: -4.8204

Max Act: 4.6801. Min Act: -0.1700

Data Index: 6391766 (Open Web Text)

Max Activating Token Index: 840

Text #18

Max Range: 4.8204. Min Range: -4.8204

Max Act: 4.7564. Min Act: -0.1700

Data Index: 8228711 (Open Web Text)

Max Activating Token Index: 976

Text #19

Max Range: 4.8204. Min Range: -4.8204

Max Act: 4.7116. Min Act: -0.1700

Data Index: 97723 (Open Web Text)

Max Activating Token Index: 874