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

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

Neuron 5242 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2567. Min Act: -0.0000

Data Index: 1086832 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1514. Min Act: -0.0000

Data Index: 241928 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1564. Min Act: -0.0000

Data Index: 629146 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1415. Min Act: -0.0000

Data Index: 116369 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1406. Min Act: -0.0000

Data Index: 675990 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1332. Min Act: -0.0000

Data Index: 608461 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1251. Min Act: -0.0001

Data Index: 253311 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1357. Min Act: -0.0000

Data Index: 1082827 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1264. Min Act: -0.0001

Data Index: 670593 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1295. Min Act: -0.0000

Data Index: 294498 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1276. Min Act: -0.0000

Data Index: 11559 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1294. Min Act: -0.0000

Data Index: 1220663 (C4 (Web Text))

Max Activating Token Index: 580

Text #12

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1196. Min Act: -0.0000

Data Index: 1200174 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1129. Min Act: -0.0000

Data Index: 176399 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1152. Min Act: -0.0000

Data Index: 1156502 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1141. Min Act: -0.0000

Data Index: 85588 (C4 (Web Text))

Max Activating Token Index: 229

Text #16

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1123. Min Act: -0.0000

Data Index: 46490 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1146. Min Act: -0.0000

Data Index: 1046338 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1098. Min Act: -0.0000

Data Index: 110587 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1085. Min Act: -0.0000

Data Index: 1051773 (C4 (Web Text))

Max Activating Token Index: 995