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

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

Neuron 845 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0288. Min Act: -0.0005

Data Index: 315010 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0311. Min Act: -0.0005

Data Index: 229786 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0291. Min Act: -0.0005

Data Index: 1284016 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0261. Min Act: -0.0005

Data Index: 487835 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0241. Min Act: -0.0005

Data Index: 584672 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0217. Min Act: -0.0005

Data Index: 126638 (C4 (Web Text))

Max Activating Token Index: 482

Text #6

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0229. Min Act: -0.0005

Data Index: 451572 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0226. Min Act: -0.0005

Data Index: 415746 (C4 (Web Text))

Max Activating Token Index: 989

Text #8

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0202. Min Act: -0.0004

Data Index: 452140 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0199. Min Act: -0.0005

Data Index: 1639075 (Python Code)

Max Activating Token Index: 151

Text #10

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0183. Min Act: -0.0005

Data Index: 1491919 (Python Code)

Max Activating Token Index: 694

Text #11

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0190. Min Act: -0.0005

Data Index: 663059 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0164. Min Act: -0.0005

Data Index: 603181 (C4 (Web Text))

Max Activating Token Index: 481

Text #13

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0200. Min Act: -0.0005

Data Index: 257766 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0213. Min Act: -0.0005

Data Index: 350014 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0202. Min Act: -0.0005

Data Index: 1029592 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0203. Min Act: -0.0005

Data Index: 1555761 (Python Code)

Max Activating Token Index: 259

Text #17

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0214. Min Act: -0.0005

Data Index: 182392 (C4 (Web Text))

Max Activating Token Index: 964

Text #18

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0188. Min Act: -0.0005

Data Index: 1402613 (Python Code)

Max Activating Token Index: 985

Text #19

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0178. Min Act: -0.0005

Data Index: 1516600 (Python Code)

Max Activating Token Index: 210