Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 558 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0216. Min Act: -0.0001

Data Index: 1085356 (C4 (Web Text))

Max Activating Token Index: 982

Text #1

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0213. Min Act: -0.0001

Data Index: 621216 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0194. Min Act: -0.0001

Data Index: 606490 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0191. Min Act: -0.0001

Data Index: 380421 (C4 (Web Text))

Max Activating Token Index: 598

Text #4

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0188. Min Act: -0.0001

Data Index: 434239 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0187. Min Act: -0.0001

Data Index: 126288 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0182. Min Act: -0.0001

Data Index: 915966 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0181. Min Act: -0.0001

Data Index: 483784 (C4 (Web Text))

Max Activating Token Index: 413

Text #8

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0186. Min Act: -0.0001

Data Index: 490231 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0181. Min Act: -0.0001

Data Index: 520283 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0179. Min Act: -0.0001

Data Index: 795419 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0175. Min Act: -0.0001

Data Index: 87433 (C4 (Web Text))

Max Activating Token Index: 1001

Text #12

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0172. Min Act: -0.0001

Data Index: 1325786 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0170. Min Act: -0.0001

Data Index: 1152312 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0168. Min Act: -0.0001

Data Index: 1263171 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0170. Min Act: -0.0001

Data Index: 1002735 (C4 (Web Text))

Max Activating Token Index: 357

Text #16

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0169. Min Act: -0.0001

Data Index: 53303 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0167. Min Act: -0.0001

Data Index: 245562 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0167. Min Act: -0.0001

Data Index: 1061804 (C4 (Web Text))

Max Activating Token Index: 708

Text #19

Max Range: 0.0216. Min Range: -0.0216

Max Act: 0.0164. Min Act: -0.0001

Data Index: 1358710 (C4 (Web Text))

Max Activating Token Index: 187