Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 61 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0267. Min Act: -0.0003

Data Index: 854930 (C4 (Web Text))

Max Activating Token Index: 974

Text #1

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0253. Min Act: -0.0003

Data Index: 512908 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0250. Min Act: -0.0003

Data Index: 1172570 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0244. Min Act: -0.0003

Data Index: 998991 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0244. Min Act: -0.0003

Data Index: 243324 (C4 (Web Text))

Max Activating Token Index: 448

Text #5

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0250. Min Act: -0.0003

Data Index: 454249 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0244. Min Act: -0.0003

Data Index: 354299 (C4 (Web Text))

Max Activating Token Index: 754

Text #7

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0239. Min Act: -0.0003

Data Index: 1300010 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0243. Min Act: -0.0003

Data Index: 1198028 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0232. Min Act: -0.0003

Data Index: 1411906 (Python Code)

Max Activating Token Index: 801

Text #10

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0235. Min Act: -0.0003

Data Index: 320877 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0235. Min Act: -0.0002

Data Index: 64941 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0229. Min Act: -0.0003

Data Index: 1119195 (C4 (Web Text))

Max Activating Token Index: 492

Text #13

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0233. Min Act: -0.0003

Data Index: 1509407 (Python Code)

Max Activating Token Index: 828

Text #14

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0238. Min Act: -0.0003

Data Index: 1211601 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0233. Min Act: -0.0003

Data Index: 870087 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0228. Min Act: -0.0003

Data Index: 1339230 (C4 (Web Text))

Max Activating Token Index: 674

Text #17

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0232. Min Act: -0.0003

Data Index: 524335 (C4 (Web Text))

Max Activating Token Index: 546

Text #18

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0228. Min Act: -0.0003

Data Index: 199093 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0212. Min Act: -0.0003

Data Index: 1285261 (C4 (Web Text))

Max Activating Token Index: 728