Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 310 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0262. Min Act: -0.0001

Data Index: 571963 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0247. Min Act: -0.0001

Data Index: 180097 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0264. Min Act: -0.0001

Data Index: 1246036 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0263. Min Act: -0.0001

Data Index: 1458415 (Python Code)

Max Activating Token Index: 10

Text #4

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0254. Min Act: -0.0001

Data Index: 1157587 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0241. Min Act: -0.0001

Data Index: 815977 (C4 (Web Text))

Max Activating Token Index: 503

Text #6

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0241. Min Act: -0.0001

Data Index: 525784 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0243. Min Act: -0.0001

Data Index: 422531 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0232. Min Act: -0.0001

Data Index: 1048284 (C4 (Web Text))

Max Activating Token Index: 565

Text #9

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0220. Min Act: -0.0001

Data Index: 710672 (C4 (Web Text))

Max Activating Token Index: 53

Text #10

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0221. Min Act: -0.0001

Data Index: 1378305 (Python Code)

Max Activating Token Index: 912

Text #11

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0229. Min Act: -0.0001

Data Index: 1009186 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0226. Min Act: -0.0001

Data Index: 647037 (C4 (Web Text))

Max Activating Token Index: 437

Text #13

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0228. Min Act: -0.0001

Data Index: 319319 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0218. Min Act: -0.0001

Data Index: 1267151 (C4 (Web Text))

Max Activating Token Index: 550

Text #15

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0226. Min Act: -0.0001

Data Index: 1380612 (Python Code)

Max Activating Token Index: 26

Text #16

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0225. Min Act: -0.0001

Data Index: 1005851 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0228. Min Act: -0.0001

Data Index: 858380 (C4 (Web Text))

Max Activating Token Index: 602

Text #18

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0233. Min Act: -0.0001

Data Index: 1555383 (Python Code)

Max Activating Token Index: 30

Text #19

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0215. Min Act: -0.0001

Data Index: 45917 (C4 (Web Text))

Max Activating Token Index: 748