Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1030 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0247. Min Act: -0.0006

Data Index: 261980 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0233. Min Act: -0.0006

Data Index: 132137 (C4 (Web Text))

Max Activating Token Index: 594

Text #2

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0203. Min Act: -0.0006

Data Index: 930807 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0203. Min Act: -0.0006

Data Index: 818531 (C4 (Web Text))

Max Activating Token Index: 276

Text #4

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0189. Min Act: -0.0006

Data Index: 544371 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0192. Min Act: -0.0006

Data Index: 452027 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0188. Min Act: -0.0006

Data Index: 931142 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0185. Min Act: -0.0006

Data Index: 310326 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0186. Min Act: -0.0006

Data Index: 86608 (C4 (Web Text))

Max Activating Token Index: 482

Text #9

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0184. Min Act: -0.0006

Data Index: 115758 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0174. Min Act: -0.0006

Data Index: 736215 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0176. Min Act: -0.0006

Data Index: 446182 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0177. Min Act: -0.0006

Data Index: 294994 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0168. Min Act: -0.0006

Data Index: 184675 (C4 (Web Text))

Max Activating Token Index: 244

Text #14

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0164. Min Act: -0.0006

Data Index: 754776 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0164. Min Act: -0.0006

Data Index: 1090980 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0163. Min Act: -0.0006

Data Index: 1080088 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0165. Min Act: -0.0006

Data Index: 891031 (C4 (Web Text))

Max Activating Token Index: 298

Text #18

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0168. Min Act: -0.0006

Data Index: 447802 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0168. Min Act: -0.0006

Data Index: 210125 (C4 (Web Text))

Max Activating Token Index: 727