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

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

Neuron 3527 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6392. Min Range: -1.6392

Max Act: 1.6392. Min Act: -0.0000

Data Index: 1219501 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 1.6392. Min Range: -1.6392

Max Act: 1.5004. Min Act: -0.0000

Data Index: 442180 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 1.6392. Min Range: -1.6392

Max Act: 1.5025. Min Act: -0.0000

Data Index: 813113 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 1.6392. Min Range: -1.6392

Max Act: 1.5217. Min Act: -0.0000

Data Index: 85350 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 1.6392. Min Range: -1.6392

Max Act: 1.4589. Min Act: -0.0000

Data Index: 1015647 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 1.6392. Min Range: -1.6392

Max Act: 1.4580. Min Act: -0.0000

Data Index: 1066151 (C4 (Web Text))

Max Activating Token Index: 673

Text #6

Max Range: 1.6392. Min Range: -1.6392

Max Act: 1.4209. Min Act: -0.0000

Data Index: 587391 (C4 (Web Text))

Max Activating Token Index: 433

Text #7

Max Range: 1.6392. Min Range: -1.6392

Max Act: 1.4200. Min Act: -0.0000

Data Index: 1190786 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 1.6392. Min Range: -1.6392

Max Act: 1.3677. Min Act: -0.0000

Data Index: 489010 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 1.6392. Min Range: -1.6392

Max Act: 1.4545. Min Act: -0.0000

Data Index: 394577 (C4 (Web Text))

Max Activating Token Index: 792

Text #10

Max Range: 1.6392. Min Range: -1.6392

Max Act: 1.3723. Min Act: -0.0000

Data Index: 920794 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 1.6392. Min Range: -1.6392

Max Act: 1.4393. Min Act: -0.0000

Data Index: 1070402 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 1.6392. Min Range: -1.6392

Max Act: 1.2807. Min Act: -0.0000

Data Index: 617231 (C4 (Web Text))

Max Activating Token Index: 884

Text #13

Max Range: 1.6392. Min Range: -1.6392

Max Act: 1.3484. Min Act: -0.0000

Data Index: 385470 (C4 (Web Text))

Max Activating Token Index: 698

Text #14

Max Range: 1.6392. Min Range: -1.6392

Max Act: 1.3329. Min Act: -0.0000

Data Index: 1321038 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 1.6392. Min Range: -1.6392

Max Act: 1.3309. Min Act: -0.0000

Data Index: 874472 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 1.6392. Min Range: -1.6392

Max Act: 1.3244. Min Act: -0.0000

Data Index: 62323 (C4 (Web Text))

Max Activating Token Index: 549

Text #17

Max Range: 1.6392. Min Range: -1.6392

Max Act: 1.3145. Min Act: -0.0000

Data Index: 639675 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 1.6392. Min Range: -1.6392

Max Act: 1.3981. Min Act: -0.0000

Data Index: 1013246 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 1.6392. Min Range: -1.6392

Max Act: 1.3089. Min Act: -0.0000

Data Index: 1640825 (Python Code)

Max Activating Token Index: 353