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

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

Neuron 115 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0309. Min Act: -0.0003

Data Index: 1533265 (Python Code)

Max Activating Token Index: 567

Text #1

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0256. Min Act: -0.0003

Data Index: 1512680 (Python Code)

Max Activating Token Index: 762

Text #2

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0282. Min Act: -0.0003

Data Index: 489513 (C4 (Web Text))

Max Activating Token Index: 61

Text #3

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0286. Min Act: -0.0003

Data Index: 1106036 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0244. Min Act: -0.0003

Data Index: 1489235 (Python Code)

Max Activating Token Index: 850

Text #5

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0274. Min Act: -0.0003

Data Index: 539189 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0269. Min Act: -0.0003

Data Index: 1031161 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0256. Min Act: -0.0003

Data Index: 1029818 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0278. Min Act: -0.0003

Data Index: 1053973 (C4 (Web Text))

Max Activating Token Index: 471

Text #9

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0263. Min Act: -0.0003

Data Index: 1086427 (C4 (Web Text))

Max Activating Token Index: 708

Text #10

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0263. Min Act: -0.0003

Data Index: 76894 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0251. Min Act: -0.0003

Data Index: 776989 (C4 (Web Text))

Max Activating Token Index: 747

Text #12

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0279. Min Act: -0.0003

Data Index: 999803 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0245. Min Act: -0.0003

Data Index: 1581672 (Python Code)

Max Activating Token Index: 149

Text #14

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0254. Min Act: -0.0003

Data Index: 450628 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0244. Min Act: -0.0003

Data Index: 1249381 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0256. Min Act: -0.0003

Data Index: 885667 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0244. Min Act: -0.0003

Data Index: 1055015 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0262. Min Act: -0.0003

Data Index: 788410 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0258. Min Act: -0.0003

Data Index: 1474402 (Python Code)

Max Activating Token Index: 999