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

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

Neuron 3321 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1754. Min Act: -0.0002

Data Index: 124122 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1393. Min Act: -0.0002

Data Index: 1245803 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1366. Min Act: -0.0002

Data Index: 552459 (C4 (Web Text))

Max Activating Token Index: 514

Text #3

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1360. Min Act: -0.0002

Data Index: 454053 (C4 (Web Text))

Max Activating Token Index: 729

Text #4

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1223. Min Act: -0.0002

Data Index: 636805 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1338. Min Act: -0.0002

Data Index: 35727 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1277. Min Act: -0.0002

Data Index: 929711 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1232. Min Act: -0.0002

Data Index: 1115829 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1231. Min Act: -0.0002

Data Index: 518982 (C4 (Web Text))

Max Activating Token Index: 876

Text #9

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1171. Min Act: -0.0002

Data Index: 1200976 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1240. Min Act: -0.0002

Data Index: 312613 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1194. Min Act: -0.0002

Data Index: 173640 (C4 (Web Text))

Max Activating Token Index: 912

Text #12

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1224. Min Act: -0.0002

Data Index: 795959 (C4 (Web Text))

Max Activating Token Index: 649

Text #13

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1151. Min Act: -0.0002

Data Index: 452292 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1150. Min Act: -0.0002

Data Index: 255621 (C4 (Web Text))

Max Activating Token Index: 191

Text #15

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1113. Min Act: -0.0002

Data Index: 192176 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1110. Min Act: -0.0002

Data Index: 743022 (C4 (Web Text))

Max Activating Token Index: 787

Text #17

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1178. Min Act: -0.0002

Data Index: 770767 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1107. Min Act: -0.0002

Data Index: 1169902 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 0.1754. Min Range: -0.1754

Max Act: 0.1135. Min Act: -0.0002

Data Index: 175939 (C4 (Web Text))

Max Activating Token Index: 730