Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1416 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1396. Min Act: -0.0004

Data Index: 1197557 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1336. Min Act: -0.0004

Data Index: 607201 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1183. Min Act: -0.0004

Data Index: 800723 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1203. Min Act: -0.0004

Data Index: 763003 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1240. Min Act: -0.0004

Data Index: 74271 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1150. Min Act: -0.0004

Data Index: 622507 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1143. Min Act: -0.0004

Data Index: 791604 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1297. Min Act: -0.0004

Data Index: 1116238 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1196. Min Act: -0.0004

Data Index: 1246531 (C4 (Web Text))

Max Activating Token Index: 160

Text #9

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1274. Min Act: -0.0004

Data Index: 194663 (C4 (Web Text))

Max Activating Token Index: 91

Text #10

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1133. Min Act: -0.0004

Data Index: 156326 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1231. Min Act: -0.0004

Data Index: 1011359 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1000. Min Act: -0.0004

Data Index: 653013 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1080. Min Act: -0.0004

Data Index: 1177320 (C4 (Web Text))

Max Activating Token Index: 297

Text #14

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1121. Min Act: -0.0004

Data Index: 1033122 (C4 (Web Text))

Max Activating Token Index: 987

Text #15

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1118. Min Act: -0.0004

Data Index: 588560 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1252. Min Act: -0.0004

Data Index: 960508 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.0948. Min Act: -0.0004

Data Index: 505360 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1050. Min Act: -0.0004

Data Index: 307130 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 0.1396. Min Range: -0.1396

Max Act: 0.1178. Min Act: -0.0004

Data Index: 919313 (C4 (Web Text))

Max Activating Token Index: 832