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

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

Neuron 1938 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0228. Min Act: -0.0005

Data Index: 1519844 (Python Code)

Max Activating Token Index: 587

Text #1

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0232. Min Act: -0.0005

Data Index: 1160875 (C4 (Web Text))

Max Activating Token Index: 339

Text #2

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0229. Min Act: -0.0005

Data Index: 1168103 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0218. Min Act: -0.0005

Data Index: 1404469 (Python Code)

Max Activating Token Index: 802

Text #4

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0217. Min Act: -0.0005

Data Index: 210048 (C4 (Web Text))

Max Activating Token Index: 561

Text #5

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0209. Min Act: -0.0005

Data Index: 117028 (C4 (Web Text))

Max Activating Token Index: 466

Text #6

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0212. Min Act: -0.0005

Data Index: 783779 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0216. Min Act: -0.0005

Data Index: 446454 (C4 (Web Text))

Max Activating Token Index: 115

Text #8

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0210. Min Act: -0.0005

Data Index: 1070996 (C4 (Web Text))

Max Activating Token Index: 59

Text #9

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0207. Min Act: -0.0005

Data Index: 543660 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0210. Min Act: -0.0005

Data Index: 907137 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0214. Min Act: -0.0005

Data Index: 56497 (C4 (Web Text))

Max Activating Token Index: 712

Text #12

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0203. Min Act: -0.0005

Data Index: 539071 (C4 (Web Text))

Max Activating Token Index: 964

Text #13

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0203. Min Act: -0.0005

Data Index: 1087381 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0187. Min Act: -0.0005

Data Index: 35133 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0204. Min Act: -0.0005

Data Index: 144571 (C4 (Web Text))

Max Activating Token Index: 955

Text #16

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0191. Min Act: -0.0005

Data Index: 187758 (C4 (Web Text))

Max Activating Token Index: 777

Text #17

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0199. Min Act: -0.0005

Data Index: 1289614 (C4 (Web Text))

Max Activating Token Index: 588

Text #18

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0189. Min Act: -0.0005

Data Index: 159355 (C4 (Web Text))

Max Activating Token Index: 481

Text #19

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0195. Min Act: -0.0005

Data Index: 853817 (C4 (Web Text))

Max Activating Token Index: 220