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

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

Neuron 3900 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: 0.0195. Min Range: -0.0195

Max Act: 0.0195. Min Act: -0.0001

Data Index: 837333 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0188. Min Act: -0.0001

Data Index: 586272 (C4 (Web Text))

Max Activating Token Index: 231

Text #2

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0186. Min Act: -0.0001

Data Index: 223792 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0185. Min Act: -0.0001

Data Index: 1210480 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0181. Min Act: -0.0001

Data Index: 1029205 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0181. Min Act: -0.0002

Data Index: 157427 (C4 (Web Text))

Max Activating Token Index: 260

Text #6

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0182. Min Act: -0.0001

Data Index: 7928 (C4 (Web Text))

Max Activating Token Index: 211

Text #7

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0178. Min Act: -0.0001

Data Index: 1184591 (C4 (Web Text))

Max Activating Token Index: 949

Text #8

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0180. Min Act: -0.0001

Data Index: 1345451 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0177. Min Act: -0.0001

Data Index: 745911 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0179. Min Act: -0.0001

Data Index: 1112125 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0178. Min Act: -0.0001

Data Index: 931640 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0175. Min Act: -0.0001

Data Index: 423247 (C4 (Web Text))

Max Activating Token Index: 871

Text #13

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0174. Min Act: -0.0001

Data Index: 21681 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0174. Min Act: -0.0002

Data Index: 436902 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0172. Min Act: -0.0001

Data Index: 1122077 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0173. Min Act: -0.0001

Data Index: 689688 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0171. Min Act: -0.0001

Data Index: 669281 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0172. Min Act: -0.0001

Data Index: 269397 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0173. Min Act: -0.0001

Data Index: 507761 (C4 (Web Text))

Max Activating Token Index: 92