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

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

Neuron 123 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: 1.5257. Min Range: -1.5257

Max Act: 1.5257. Min Act: -0.0000

Data Index: 524048 (C4 (Web Text))

Max Activating Token Index: 950

Text #1

Max Range: 1.5257. Min Range: -1.5257

Max Act: 1.2353. Min Act: -0.0000

Data Index: 972935 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 1.5257. Min Range: -1.5257

Max Act: 1.0590. Min Act: -0.0000

Data Index: 25177 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 1.5257. Min Range: -1.5257

Max Act: 1.0204. Min Act: -0.0000

Data Index: 1286447 (C4 (Web Text))

Max Activating Token Index: 413

Text #4

Max Range: 1.5257. Min Range: -1.5257

Max Act: 0.9833. Min Act: -0.0000

Data Index: 76099 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 1.5257. Min Range: -1.5257

Max Act: 1.0107. Min Act: -0.0000

Data Index: 1019317 (C4 (Web Text))

Max Activating Token Index: 1002

Text #6

Max Range: 1.5257. Min Range: -1.5257

Max Act: 0.9970. Min Act: -0.0000

Data Index: 942842 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 1.5257. Min Range: -1.5257

Max Act: 0.9753. Min Act: -0.0000

Data Index: 479229 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 1.5257. Min Range: -1.5257

Max Act: 0.9346. Min Act: -0.0000

Data Index: 636577 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 1.5257. Min Range: -1.5257

Max Act: 0.8899. Min Act: -0.0000

Data Index: 646024 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 1.5257. Min Range: -1.5257

Max Act: 0.9157. Min Act: -0.0000

Data Index: 867724 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 1.5257. Min Range: -1.5257

Max Act: 0.9152. Min Act: -0.0000

Data Index: 235178 (C4 (Web Text))

Max Activating Token Index: 30

Text #12

Max Range: 1.5257. Min Range: -1.5257

Max Act: 0.8312. Min Act: -0.0000

Data Index: 684531 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 1.5257. Min Range: -1.5257

Max Act: 0.8539. Min Act: -0.0000

Data Index: 1151187 (C4 (Web Text))

Max Activating Token Index: 370

Text #14

Max Range: 1.5257. Min Range: -1.5257

Max Act: 0.8244. Min Act: -0.0000

Data Index: 336973 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 1.5257. Min Range: -1.5257

Max Act: 0.8077. Min Act: -0.0000

Data Index: 287746 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 1.5257. Min Range: -1.5257

Max Act: 0.7961. Min Act: -0.0000

Data Index: 448877 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 1.5257. Min Range: -1.5257

Max Act: 0.8377. Min Act: -0.0000

Data Index: 361826 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 1.5257. Min Range: -1.5257

Max Act: 0.8390. Min Act: -0.0000

Data Index: 1004401 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 1.5257. Min Range: -1.5257

Max Act: 0.8349. Min Act: -0.0000

Data Index: 742692 (C4 (Web Text))

Max Activating Token Index: 468