Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2149 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.3067. Min Act: -0.0000

Data Index: 387589 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2838. Min Act: -0.0000

Data Index: 84568 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2816. Min Act: -0.0000

Data Index: 1234787 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2686. Min Act: -0.0000

Data Index: 399307 (C4 (Web Text))

Max Activating Token Index: 702

Text #4

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2546. Min Act: -0.0000

Data Index: 856259 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2438. Min Act: -0.0000

Data Index: 238113 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2479. Min Act: -0.0000

Data Index: 617705 (C4 (Web Text))

Max Activating Token Index: 602

Text #7

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2196. Min Act: -0.0000

Data Index: 1219774 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2439. Min Act: -0.0000

Data Index: 21100 (C4 (Web Text))

Max Activating Token Index: 567

Text #9

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2368. Min Act: -0.0000

Data Index: 874177 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2278. Min Act: -0.0000

Data Index: 214617 (C4 (Web Text))

Max Activating Token Index: 135

Text #11

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2350. Min Act: -0.0000

Data Index: 102345 (C4 (Web Text))

Max Activating Token Index: 805

Text #12

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2442. Min Act: -0.0000

Data Index: 363665 (C4 (Web Text))

Max Activating Token Index: 854

Text #13

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2168. Min Act: -0.0000

Data Index: 1071961 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2343. Min Act: -0.0000

Data Index: 1136592 (C4 (Web Text))

Max Activating Token Index: 491

Text #15

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2315. Min Act: -0.0000

Data Index: 480121 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2143. Min Act: -0.0000

Data Index: 1177296 (C4 (Web Text))

Max Activating Token Index: 575

Text #17

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2166. Min Act: -0.0000

Data Index: 1168889 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2315. Min Act: -0.0000

Data Index: 526153 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2164. Min Act: -0.0000

Data Index: 27571 (C4 (Web Text))

Max Activating Token Index: 203