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

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

Neuron 2045 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: 0.0195. Min Range: -0.0195

Max Act: 0.0192. Min Act: -0.0005

Data Index: 4059 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0195. Min Act: -0.0005

Data Index: 620108 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0182. Min Act: -0.0005

Data Index: 1237355 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0154. Min Act: -0.0005

Data Index: 1092653 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0195. Min Act: -0.0005

Data Index: 1292131 (C4 (Web Text))

Max Activating Token Index: 798

Text #5

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0164. Min Act: -0.0005

Data Index: 1093560 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0181. Min Act: -0.0005

Data Index: 1167401 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0146. Min Act: -0.0005

Data Index: 356861 (C4 (Web Text))

Max Activating Token Index: 587

Text #8

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0167. Min Act: -0.0005

Data Index: 535566 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0170. Min Act: -0.0005

Data Index: 1440103 (Python Code)

Max Activating Token Index: 913

Text #10

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0171. Min Act: -0.0005

Data Index: 1490345 (Python Code)

Max Activating Token Index: 311

Text #11

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0176. Min Act: -0.0005

Data Index: 1554635 (Python Code)

Max Activating Token Index: 15

Text #12

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0171. Min Act: -0.0004

Data Index: 1581658 (Python Code)

Max Activating Token Index: 955

Text #13

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0171. Min Act: -0.0004

Data Index: 1561130 (Python Code)

Max Activating Token Index: 69

Text #14

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0171. Min Act: -0.0005

Data Index: 1528504 (Python Code)

Max Activating Token Index: 971

Text #15

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0171. Min Act: -0.0005

Data Index: 859656 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0149. Min Act: -0.0005

Data Index: 1422206 (Python Code)

Max Activating Token Index: 496

Text #17

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0161. Min Act: -0.0005

Data Index: 1394656 (Python Code)

Max Activating Token Index: 628

Text #18

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0178. Min Act: -0.0005

Data Index: 18935 (C4 (Web Text))

Max Activating Token Index: 790

Text #19

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0165. Min Act: -0.0005

Data Index: 160420 (C4 (Web Text))

Max Activating Token Index: 320