Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3194 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.4987. Min Act: -0.0000

Data Index: 328895 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.4468. Min Act: -0.0000

Data Index: 873622 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.4189. Min Act: -0.0000

Data Index: 471087 (C4 (Web Text))

Max Activating Token Index: 151

Text #3

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3509. Min Act: -0.0000

Data Index: 347113 (C4 (Web Text))

Max Activating Token Index: 518

Text #4

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3553. Min Act: -0.0000

Data Index: 706308 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3268. Min Act: -0.0000

Data Index: 1147630 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3481. Min Act: -0.0000

Data Index: 58995 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3203. Min Act: -0.0000

Data Index: 1226842 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3442. Min Act: -0.0000

Data Index: 240920 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3256. Min Act: -0.0000

Data Index: 712738 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3136. Min Act: -0.0000

Data Index: 54127 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3460. Min Act: -0.0000

Data Index: 1199250 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3279. Min Act: -0.0000

Data Index: 1272836 (C4 (Web Text))

Max Activating Token Index: 903

Text #13

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3148. Min Act: -0.0000

Data Index: 796595 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3164. Min Act: -0.0000

Data Index: 1228299 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3101. Min Act: -0.0000

Data Index: 489966 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3058. Min Act: -0.0000

Data Index: 1103033 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3059. Min Act: -0.0000

Data Index: 736347 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3055. Min Act: -0.0000

Data Index: 508222 (C4 (Web Text))

Max Activating Token Index: 398

Text #19

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3279. Min Act: -0.0000

Data Index: 740455 (C4 (Web Text))

Max Activating Token Index: 337