Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 596 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0359. Min Act: -0.0006

Data Index: 502116 (C4 (Web Text))

Max Activating Token Index: 825

Text #1

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0316. Min Act: -0.0006

Data Index: 1267561 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0300. Min Act: -0.0006

Data Index: 166572 (C4 (Web Text))

Max Activating Token Index: 177

Text #3

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0250. Min Act: -0.0006

Data Index: 560816 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0244. Min Act: -0.0006

Data Index: 796215 (C4 (Web Text))

Max Activating Token Index: 946

Text #5

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0237. Min Act: -0.0006

Data Index: 247388 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0231. Min Act: -0.0006

Data Index: 1324233 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0243. Min Act: -0.0006

Data Index: 289960 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0248. Min Act: -0.0006

Data Index: 14378 (C4 (Web Text))

Max Activating Token Index: 553

Text #9

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0248. Min Act: -0.0006

Data Index: 306797 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0236. Min Act: -0.0006

Data Index: 879600 (C4 (Web Text))

Max Activating Token Index: 878

Text #11

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0228. Min Act: -0.0006

Data Index: 765669 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0217. Min Act: -0.0006

Data Index: 584108 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0221. Min Act: -0.0006

Data Index: 40797 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0220. Min Act: -0.0006

Data Index: 670104 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0218. Min Act: -0.0006

Data Index: 625454 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0221. Min Act: -0.0006

Data Index: 1202338 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0215. Min Act: -0.0006

Data Index: 691020 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0209. Min Act: -0.0006

Data Index: 912004 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0208. Min Act: -0.0006

Data Index: 185517 (C4 (Web Text))

Max Activating Token Index: 491