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

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

Neuron 3404 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.3025. Min Act: -0.0000

Data Index: 454804 (C4 (Web Text))

Max Activating Token Index: 964

Text #1

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2972. Min Act: -0.0000

Data Index: 145659 (C4 (Web Text))

Max Activating Token Index: 379

Text #2

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2849. Min Act: -0.0000

Data Index: 761634 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2789. Min Act: -0.0000

Data Index: 546419 (C4 (Web Text))

Max Activating Token Index: 667

Text #4

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2645. Min Act: -0.0000

Data Index: 1314102 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2772. Min Act: -0.0000

Data Index: 1301382 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2619. Min Act: -0.0000

Data Index: 713415 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2592. Min Act: -0.0000

Data Index: 871735 (C4 (Web Text))

Max Activating Token Index: 431

Text #8

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2589. Min Act: -0.0000

Data Index: 298175 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2326. Min Act: -0.0000

Data Index: 41695 (C4 (Web Text))

Max Activating Token Index: 451

Text #10

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2279. Min Act: -0.0000

Data Index: 947148 (C4 (Web Text))

Max Activating Token Index: 1017

Text #11

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2202. Min Act: -0.0000

Data Index: 225482 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2408. Min Act: -0.0000

Data Index: 1072631 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2184. Min Act: -0.0000

Data Index: 1057900 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2220. Min Act: -0.0000

Data Index: 416259 (C4 (Web Text))

Max Activating Token Index: 736

Text #15

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2118. Min Act: -0.0000

Data Index: 920634 (C4 (Web Text))

Max Activating Token Index: 500

Text #16

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2020. Min Act: -0.0000

Data Index: 1335426 (C4 (Web Text))

Max Activating Token Index: 300

Text #17

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2219. Min Act: -0.0000

Data Index: 762999 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2163. Min Act: -0.0000

Data Index: 1222798 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2043. Min Act: -0.0000

Data Index: 221134 (C4 (Web Text))

Max Activating Token Index: 907