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

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

Neuron 2060 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: 6.0755. Min Range: -6.0755

Max Act: 6.0755. Min Act: -0.0000

Data Index: 539479 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 6.0755. Min Range: -6.0755

Max Act: 5.2170. Min Act: -0.0000

Data Index: 560659 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 6.0755. Min Range: -6.0755

Max Act: 4.9709. Min Act: -0.0000

Data Index: 75437 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 6.0755. Min Range: -6.0755

Max Act: 4.9256. Min Act: -0.0000

Data Index: 237859 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 6.0755. Min Range: -6.0755

Max Act: 4.8620. Min Act: -0.0000

Data Index: 599308 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 6.0755. Min Range: -6.0755

Max Act: 4.7555. Min Act: -0.0000

Data Index: 1302805 (C4 (Web Text))

Max Activating Token Index: 358

Text #6

Max Range: 6.0755. Min Range: -6.0755

Max Act: 4.3212. Min Act: -0.0000

Data Index: 707399 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 6.0755. Min Range: -6.0755

Max Act: 4.5925. Min Act: -0.0000

Data Index: 488438 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 6.0755. Min Range: -6.0755

Max Act: 4.0539. Min Act: -0.0000

Data Index: 1056616 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 6.0755. Min Range: -6.0755

Max Act: 4.3779. Min Act: -0.0000

Data Index: 811589 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 6.0755. Min Range: -6.0755

Max Act: 4.3756. Min Act: -0.0000

Data Index: 1065899 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 6.0755. Min Range: -6.0755

Max Act: 4.3047. Min Act: -0.0000

Data Index: 754425 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 6.0755. Min Range: -6.0755

Max Act: 4.3170. Min Act: -0.0000

Data Index: 1009378 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 6.0755. Min Range: -6.0755

Max Act: 4.4682. Min Act: -0.0000

Data Index: 1316319 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 6.0755. Min Range: -6.0755

Max Act: 3.9351. Min Act: -0.0000

Data Index: 878495 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 6.0755. Min Range: -6.0755

Max Act: 4.0354. Min Act: -0.0000

Data Index: 945941 (C4 (Web Text))

Max Activating Token Index: 706

Text #16

Max Range: 6.0755. Min Range: -6.0755

Max Act: 4.1290. Min Act: -0.0000

Data Index: 138532 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 6.0755. Min Range: -6.0755

Max Act: 4.1778. Min Act: -0.0000

Data Index: 646823 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 6.0755. Min Range: -6.0755

Max Act: 4.2644. Min Act: -0.0000

Data Index: 842027 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 6.0755. Min Range: -6.0755

Max Act: 4.3075. Min Act: -0.0000

Data Index: 249549 (C4 (Web Text))

Max Activating Token Index: 92