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

Dataset: Open Web Text

Neuron 2496 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: 3.8271. Min Range: -3.8271

Max Act: 3.8271. Min Act: -0.1700

Data Index: 2938081 (Open Web Text)

Max Activating Token Index: 436

Text #1

Max Range: 3.8271. Min Range: -3.8271

Max Act: 3.8063. Min Act: -0.1700

Data Index: 8082970 (Open Web Text)

Max Activating Token Index: 85

Text #2

Max Range: 3.8271. Min Range: -3.8271

Max Act: 3.7910. Min Act: -0.1700

Data Index: 1101694 (Open Web Text)

Max Activating Token Index: 946

Text #3

Max Range: 3.8271. Min Range: -3.8271

Max Act: 3.7402. Min Act: -0.1700

Data Index: 7418950 (Open Web Text)

Max Activating Token Index: 258

Text #4

Max Range: 3.8271. Min Range: -3.8271

Max Act: 3.7337. Min Act: -0.1700

Data Index: 4198315 (Open Web Text)

Max Activating Token Index: 351

Text #5

Max Range: 3.8271. Min Range: -3.8271

Max Act: 3.7514. Min Act: -0.1700

Data Index: 874207 (Open Web Text)

Max Activating Token Index: 598

Text #6

Max Range: 3.8271. Min Range: -3.8271

Max Act: 3.7126. Min Act: -0.1700

Data Index: 7629317 (Open Web Text)

Max Activating Token Index: 476

Text #7

Max Range: 3.8271. Min Range: -3.8271

Max Act: 3.7225. Min Act: -0.1700

Data Index: 2342244 (Open Web Text)

Max Activating Token Index: 469

Text #8

Max Range: 3.8271. Min Range: -3.8271

Max Act: 3.7241. Min Act: -0.1700

Data Index: 5286667 (Open Web Text)

Max Activating Token Index: 149

Text #9

Max Range: 3.8271. Min Range: -3.8271

Max Act: 3.7126. Min Act: -0.1700

Data Index: 2691287 (Open Web Text)

Max Activating Token Index: 769

Text #10

Max Range: 3.8271. Min Range: -3.8271

Max Act: 3.6665. Min Act: -0.1700

Data Index: 6305327 (Open Web Text)

Max Activating Token Index: 834

Text #11

Max Range: 3.8271. Min Range: -3.8271

Max Act: 3.6890. Min Act: -0.1700

Data Index: 7173170 (Open Web Text)

Max Activating Token Index: 365

Text #12

Max Range: 3.8271. Min Range: -3.8271

Max Act: 3.6804. Min Act: -0.1700

Data Index: 3702112 (Open Web Text)

Max Activating Token Index: 735

Text #13

Max Range: 3.8271. Min Range: -3.8271

Max Act: 3.6330. Min Act: -0.1700

Data Index: 5084766 (Open Web Text)

Max Activating Token Index: 929

Text #14

Max Range: 3.8271. Min Range: -3.8271

Max Act: 3.6558. Min Act: -0.1700

Data Index: 2117619 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 3.8271. Min Range: -3.8271

Max Act: 3.6432. Min Act: -0.1700

Data Index: 6169226 (Open Web Text)

Max Activating Token Index: 117

Text #16

Max Range: 3.8271. Min Range: -3.8271

Max Act: 3.6598. Min Act: -0.1700

Data Index: 2081588 (Open Web Text)

Max Activating Token Index: 694

Text #17

Max Range: 3.8271. Min Range: -3.8271

Max Act: 3.6336. Min Act: -0.1700

Data Index: 2347205 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 3.8271. Min Range: -3.8271

Max Act: 3.6288. Min Act: -0.1700

Data Index: 2740674 (Open Web Text)

Max Activating Token Index: 85

Text #19

Max Range: 3.8271. Min Range: -3.8271

Max Act: 3.6383. Min Act: -0.1700

Data Index: 685590 (Open Web Text)

Max Activating Token Index: 469