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

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

Neuron 3993 in Layer 1

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: 0.0220. Min Range: -0.0220

Max Act: 0.0220. Min Act: -0.0002

Data Index: 174373 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0212. Min Act: -0.0002

Data Index: 629198 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0196. Min Act: -0.0002

Data Index: 649624 (C4 (Web Text))

Max Activating Token Index: 422

Text #3

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0201. Min Act: -0.0002

Data Index: 996901 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0190. Min Act: -0.0002

Data Index: 991703 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0189. Min Act: -0.0002

Data Index: 70450 (C4 (Web Text))

Max Activating Token Index: 481

Text #6

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0186. Min Act: -0.0002

Data Index: 200740 (C4 (Web Text))

Max Activating Token Index: 378

Text #7

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0185. Min Act: -0.0002

Data Index: 862617 (C4 (Web Text))

Max Activating Token Index: 430

Text #8

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0174. Min Act: -0.0002

Data Index: 566207 (C4 (Web Text))

Max Activating Token Index: 876

Text #9

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0175. Min Act: -0.0003

Data Index: 357043 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0171. Min Act: -0.0002

Data Index: 147518 (C4 (Web Text))

Max Activating Token Index: 215

Text #11

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0175. Min Act: -0.0002

Data Index: 1311607 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0174. Min Act: -0.0002

Data Index: 202525 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0171. Min Act: -0.0002

Data Index: 1575247 (Python Code)

Max Activating Token Index: 132

Text #14

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0174. Min Act: -0.0002

Data Index: 793957 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0173. Min Act: -0.0002

Data Index: 180952 (C4 (Web Text))

Max Activating Token Index: 401

Text #16

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0169. Min Act: -0.0002

Data Index: 1401823 (Python Code)

Max Activating Token Index: 83

Text #17

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0168. Min Act: -0.0002

Data Index: 171339 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0169. Min Act: -0.0002

Data Index: 97484 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0168. Min Act: -0.0002

Data Index: 1215376 (C4 (Web Text))

Max Activating Token Index: 277