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

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

Neuron 1905 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: 0.0228. Min Range: -0.0228

Max Act: 0.0228. Min Act: -0.0005

Data Index: 1602681 (Python Code)

Max Activating Token Index: 525

Text #1

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0212. Min Act: -0.0005

Data Index: 1361881 (Python Code)

Max Activating Token Index: 451

Text #2

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0204. Min Act: -0.0005

Data Index: 188656 (C4 (Web Text))

Max Activating Token Index: 880

Text #3

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0208. Min Act: -0.0005

Data Index: 1152943 (C4 (Web Text))

Max Activating Token Index: 638

Text #4

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0216. Min Act: -0.0005

Data Index: 690077 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0211. Min Act: -0.0005

Data Index: 919601 (C4 (Web Text))

Max Activating Token Index: 398

Text #6

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0215. Min Act: -0.0005

Data Index: 580357 (C4 (Web Text))

Max Activating Token Index: 594

Text #7

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0205. Min Act: -0.0005

Data Index: 294596 (C4 (Web Text))

Max Activating Token Index: 725

Text #8

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0196. Min Act: -0.0005

Data Index: 1507028 (Python Code)

Max Activating Token Index: 101

Text #9

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0197. Min Act: -0.0005

Data Index: 374250 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0207. Min Act: -0.0005

Data Index: 1369391 (Python Code)

Max Activating Token Index: 811

Text #11

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0196. Min Act: -0.0005

Data Index: 247863 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0197. Min Act: -0.0005

Data Index: 1617146 (Python Code)

Max Activating Token Index: 61

Text #13

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0193. Min Act: -0.0005

Data Index: 118545 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0198. Min Act: -0.0005

Data Index: 418280 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0198. Min Act: -0.0005

Data Index: 997217 (C4 (Web Text))

Max Activating Token Index: 528

Text #16

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0196. Min Act: -0.0005

Data Index: 1398834 (Python Code)

Max Activating Token Index: 53

Text #17

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0200. Min Act: -0.0005

Data Index: 824974 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0183. Min Act: -0.0005

Data Index: 1437283 (Python Code)

Max Activating Token Index: 553

Text #19

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0199. Min Act: -0.0005

Data Index: 839679 (C4 (Web Text))

Max Activating Token Index: 372