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

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

Neuron 976 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.4359. Min Range: -8.4359

Max Act: 8.4359. Min Act: -0.0000

Data Index: 77929 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 8.4359. Min Range: -8.4359

Max Act: 7.8762. Min Act: -0.0000

Data Index: 790566 (C4 (Web Text))

Max Activating Token Index: 852

Text #2

Max Range: 8.4359. Min Range: -8.4359

Max Act: 7.5825. Min Act: 0.0000

Data Index: 1269959 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 8.4359. Min Range: -8.4359

Max Act: 7.7587. Min Act: -0.0000

Data Index: 1608949 (Python Code)

Max Activating Token Index: 822

Text #4

Max Range: 8.4359. Min Range: -8.4359

Max Act: 7.6443. Min Act: -0.0000

Data Index: 370927 (C4 (Web Text))

Max Activating Token Index: 592

Text #5

Max Range: 8.4359. Min Range: -8.4359

Max Act: 7.6296. Min Act: -0.0000

Data Index: 1282699 (C4 (Web Text))

Max Activating Token Index: 981

Text #6

Max Range: 8.4359. Min Range: -8.4359

Max Act: 7.5827. Min Act: -0.0000

Data Index: 16509 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 8.4359. Min Range: -8.4359

Max Act: 7.3549. Min Act: -0.0000

Data Index: 1246895 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 8.4359. Min Range: -8.4359

Max Act: 7.3809. Min Act: -0.0000

Data Index: 159270 (C4 (Web Text))

Max Activating Token Index: 1010

Text #9

Max Range: 8.4359. Min Range: -8.4359

Max Act: 7.7241. Min Act: -0.0000

Data Index: 1036329 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 8.4359. Min Range: -8.4359

Max Act: 7.5256. Min Act: -0.0000

Data Index: 528679 (C4 (Web Text))

Max Activating Token Index: 412

Text #11

Max Range: 8.4359. Min Range: -8.4359

Max Act: 7.2892. Min Act: -0.0000

Data Index: 203971 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 8.4359. Min Range: -8.4359

Max Act: 7.4020. Min Act: -0.0000

Data Index: 524294 (C4 (Web Text))

Max Activating Token Index: 956

Text #13

Max Range: 8.4359. Min Range: -8.4359

Max Act: 7.2912. Min Act: -0.0000

Data Index: 320733 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 8.4359. Min Range: -8.4359

Max Act: 7.2240. Min Act: -0.0000

Data Index: 327772 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 8.4359. Min Range: -8.4359

Max Act: 7.2143. Min Act: -0.0000

Data Index: 1398748 (Python Code)

Max Activating Token Index: 640

Text #16

Max Range: 8.4359. Min Range: -8.4359

Max Act: 7.0447. Min Act: -0.0000

Data Index: 298776 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 8.4359. Min Range: -8.4359

Max Act: 7.0276. Min Act: -0.0000

Data Index: 477453 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 8.4359. Min Range: -8.4359

Max Act: 7.2230. Min Act: -0.0000

Data Index: 328170 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 8.4359. Min Range: -8.4359

Max Act: 7.0226. Min Act: -0.0000

Data Index: 761927 (C4 (Web Text))

Max Activating Token Index: 241