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

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

Neuron 1000 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0235. Min Act: -0.0005

Data Index: 325998 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0237. Min Act: -0.0006

Data Index: 86980 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0237. Min Act: -0.0005

Data Index: 421884 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0237. Min Act: -0.0006

Data Index: 1054862 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0235. Min Act: -0.0005

Data Index: 673489 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0239. Min Act: -0.0005

Data Index: 258816 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0228. Min Act: -0.0005

Data Index: 490177 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0231. Min Act: -0.0005

Data Index: 915808 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0231. Min Act: -0.0005

Data Index: 1471792 (Python Code)

Max Activating Token Index: 1014

Text #9

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0230. Min Act: -0.0005

Data Index: 1070253 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0229. Min Act: -0.0005

Data Index: 1190908 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0228. Min Act: -0.0005

Data Index: 773584 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0227. Min Act: -0.0005

Data Index: 909553 (C4 (Web Text))

Max Activating Token Index: 773

Text #13

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0228. Min Act: -0.0005

Data Index: 869130 (C4 (Web Text))

Max Activating Token Index: 1010

Text #14

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0225. Min Act: -0.0005

Data Index: 1186995 (C4 (Web Text))

Max Activating Token Index: 303

Text #15

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0214. Min Act: -0.0005

Data Index: 279128 (C4 (Web Text))

Max Activating Token Index: 875

Text #16

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0222. Min Act: -0.0005

Data Index: 55520 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0222. Min Act: -0.0005

Data Index: 1314706 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0217. Min Act: -0.0006

Data Index: 896336 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 0.0239. Min Range: -0.0239

Max Act: 0.0217. Min Act: -0.0005

Data Index: 1268551 (C4 (Web Text))

Max Activating Token Index: 199