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

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

Neuron 3392 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6446. Min Range: -2.6446

Max Act: 2.5344. Min Act: -0.0000

Data Index: 467469 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 2.6446. Min Range: -2.6446

Max Act: 2.6446. Min Act: -0.0000

Data Index: 851831 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 2.6446. Min Range: -2.6446

Max Act: 2.1630. Min Act: -0.0000

Data Index: 1007047 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 2.6446. Min Range: -2.6446

Max Act: 2.1104. Min Act: -0.0000

Data Index: 1225164 (C4 (Web Text))

Max Activating Token Index: 772

Text #4

Max Range: 2.6446. Min Range: -2.6446

Max Act: 2.0089. Min Act: -0.0000

Data Index: 831121 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 2.6446. Min Range: -2.6446

Max Act: 1.9671. Min Act: -0.0000

Data Index: 567753 (C4 (Web Text))

Max Activating Token Index: 651

Text #6

Max Range: 2.6446. Min Range: -2.6446

Max Act: 1.9625. Min Act: -0.0000

Data Index: 1986 (C4 (Web Text))

Max Activating Token Index: 514

Text #7

Max Range: 2.6446. Min Range: -2.6446

Max Act: 1.8546. Min Act: -0.0000

Data Index: 488958 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 2.6446. Min Range: -2.6446

Max Act: 1.9269. Min Act: -0.0000

Data Index: 12093 (C4 (Web Text))

Max Activating Token Index: 411

Text #9

Max Range: 2.6446. Min Range: -2.6446

Max Act: 1.8917. Min Act: -0.0000

Data Index: 387898 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 2.6446. Min Range: -2.6446

Max Act: 1.9565. Min Act: -0.0000

Data Index: 169472 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 2.6446. Min Range: -2.6446

Max Act: 1.7356. Min Act: -0.0000

Data Index: 940033 (C4 (Web Text))

Max Activating Token Index: 805

Text #12

Max Range: 2.6446. Min Range: -2.6446

Max Act: 1.7840. Min Act: -0.0000

Data Index: 961813 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 2.6446. Min Range: -2.6446

Max Act: 1.7717. Min Act: -0.0000

Data Index: 1227027 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 2.6446. Min Range: -2.6446

Max Act: 1.7505. Min Act: -0.0000

Data Index: 501567 (C4 (Web Text))

Max Activating Token Index: 675

Text #15

Max Range: 2.6446. Min Range: -2.6446

Max Act: 1.8565. Min Act: -0.0000

Data Index: 1034912 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 2.6446. Min Range: -2.6446

Max Act: 1.7041. Min Act: -0.0000

Data Index: 536304 (C4 (Web Text))

Max Activating Token Index: 244

Text #17

Max Range: 2.6446. Min Range: -2.6446

Max Act: 1.8173. Min Act: -0.0000

Data Index: 64984 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 2.6446. Min Range: -2.6446

Max Act: 1.6867. Min Act: -0.0000

Data Index: 186244 (C4 (Web Text))

Max Activating Token Index: 592

Text #19

Max Range: 2.6446. Min Range: -2.6446

Max Act: 1.5401. Min Act: -0.0000

Data Index: 209767 (C4 (Web Text))

Max Activating Token Index: 266