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

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

Neuron 5097 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 9.7279. Min Range: -9.7279

Max Act: 9.7279. Min Act: -0.0000

Data Index: 548146 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 9.7279. Min Range: -9.7279

Max Act: 9.5722. Min Act: -0.0000

Data Index: 634010 (C4 (Web Text))

Max Activating Token Index: 262

Text #2

Max Range: 9.7279. Min Range: -9.7279

Max Act: 9.6484. Min Act: -0.0000

Data Index: 314850 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 9.7279. Min Range: -9.7279

Max Act: 9.5777. Min Act: -0.0000

Data Index: 596198 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 9.7279. Min Range: -9.7279

Max Act: 9.3886. Min Act: -0.0000

Data Index: 619714 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 9.7279. Min Range: -9.7279

Max Act: 9.5366. Min Act: -0.0000

Data Index: 823978 (C4 (Web Text))

Max Activating Token Index: 555

Text #6

Max Range: 9.7279. Min Range: -9.7279

Max Act: 9.1870. Min Act: -0.0000

Data Index: 1175139 (C4 (Web Text))

Max Activating Token Index: 819

Text #7

Max Range: 9.7279. Min Range: -9.7279

Max Act: 9.2281. Min Act: -0.0000

Data Index: 251651 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 9.7279. Min Range: -9.7279

Max Act: 9.2008. Min Act: -0.0000

Data Index: 245808 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 9.7279. Min Range: -9.7279

Max Act: 9.0064. Min Act: -0.0000

Data Index: 233629 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 9.7279. Min Range: -9.7279

Max Act: 9.1622. Min Act: -0.0000

Data Index: 1004505 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 9.7279. Min Range: -9.7279

Max Act: 9.4526. Min Act: -0.0000

Data Index: 1131774 (C4 (Web Text))

Max Activating Token Index: 248

Text #12

Max Range: 9.7279. Min Range: -9.7279

Max Act: 8.7303. Min Act: -0.0000

Data Index: 1197816 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 9.7279. Min Range: -9.7279

Max Act: 8.9247. Min Act: -0.0000

Data Index: 466777 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 9.7279. Min Range: -9.7279

Max Act: 9.1964. Min Act: -0.0000

Data Index: 203850 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 9.7279. Min Range: -9.7279

Max Act: 8.9720. Min Act: -0.0000

Data Index: 88344 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 9.7279. Min Range: -9.7279

Max Act: 8.9532. Min Act: -0.0000

Data Index: 548291 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 9.7279. Min Range: -9.7279

Max Act: 8.5823. Min Act: -0.0000

Data Index: 1179935 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 9.7279. Min Range: -9.7279

Max Act: 8.5644. Min Act: -0.0000

Data Index: 84456 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 9.7279. Min Range: -9.7279

Max Act: 8.7476. Min Act: -0.0000

Data Index: 295416 (C4 (Web Text))

Max Activating Token Index: 84