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

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

Neuron 85 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: 0.0354. Min Range: -0.0354

Max Act: 0.0354. Min Act: -0.0006

Data Index: 1114989 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0277. Min Act: -0.0006

Data Index: 400391 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0243. Min Act: -0.0006

Data Index: 480096 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0235. Min Act: -0.0006

Data Index: 272067 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0218. Min Act: -0.0006

Data Index: 1269027 (C4 (Web Text))

Max Activating Token Index: 340

Text #5

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0227. Min Act: -0.0006

Data Index: 1289725 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0225. Min Act: -0.0006

Data Index: 29757 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0211. Min Act: -0.0006

Data Index: 333424 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0208. Min Act: -0.0006

Data Index: 273736 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0209. Min Act: -0.0006

Data Index: 1078116 (C4 (Web Text))

Max Activating Token Index: 466

Text #10

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0212. Min Act: -0.0006

Data Index: 651573 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0202. Min Act: -0.0006

Data Index: 869798 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0202. Min Act: -0.0006

Data Index: 771261 (C4 (Web Text))

Max Activating Token Index: 843

Text #13

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0192. Min Act: -0.0006

Data Index: 63860 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0195. Min Act: -0.0006

Data Index: 877479 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0186. Min Act: -0.0006

Data Index: 1233605 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0199. Min Act: -0.0006

Data Index: 859061 (C4 (Web Text))

Max Activating Token Index: 317

Text #17

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0194. Min Act: -0.0006

Data Index: 426149 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0190. Min Act: -0.0006

Data Index: 797227 (C4 (Web Text))

Max Activating Token Index: 225

Text #19

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0193. Min Act: -0.0006

Data Index: 255087 (C4 (Web Text))

Max Activating Token Index: 56