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

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

Neuron 4319 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: 1.4461. Min Range: -1.4461

Max Act: 1.4461. Min Act: -0.0000

Data Index: 160979 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 1.4461. Min Range: -1.4461

Max Act: 1.2035. Min Act: -0.0000

Data Index: 302253 (C4 (Web Text))

Max Activating Token Index: 1001

Text #2

Max Range: 1.4461. Min Range: -1.4461

Max Act: 1.2435. Min Act: -0.0000

Data Index: 1354908 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 1.4461. Min Range: -1.4461

Max Act: 1.2231. Min Act: -0.0000

Data Index: 633297 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 1.4461. Min Range: -1.4461

Max Act: 1.3079. Min Act: -0.0000

Data Index: 1079865 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 1.4461. Min Range: -1.4461

Max Act: 1.1924. Min Act: -0.0000

Data Index: 814655 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 1.4461. Min Range: -1.4461

Max Act: 1.2342. Min Act: -0.0000

Data Index: 177704 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 1.4461. Min Range: -1.4461

Max Act: 1.0674. Min Act: -0.0000

Data Index: 1029651 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 1.4461. Min Range: -1.4461

Max Act: 1.0692. Min Act: -0.0000

Data Index: 119009 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 1.4461. Min Range: -1.4461

Max Act: 1.0412. Min Act: -0.0000

Data Index: 1142696 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 1.4461. Min Range: -1.4461

Max Act: 1.1195. Min Act: -0.0000

Data Index: 583335 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 1.4461. Min Range: -1.4461

Max Act: 1.1767. Min Act: -0.0000

Data Index: 673008 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 1.4461. Min Range: -1.4461

Max Act: 1.0803. Min Act: -0.0000

Data Index: 1242410 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 1.4461. Min Range: -1.4461

Max Act: 1.0696. Min Act: -0.0000

Data Index: 130631 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 1.4461. Min Range: -1.4461

Max Act: 0.9945. Min Act: -0.0000

Data Index: 831955 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 1.4461. Min Range: -1.4461

Max Act: 1.1204. Min Act: -0.0000

Data Index: 220210 (C4 (Web Text))

Max Activating Token Index: 806

Text #16

Max Range: 1.4461. Min Range: -1.4461

Max Act: 1.0549. Min Act: -0.0000

Data Index: 486506 (C4 (Web Text))

Max Activating Token Index: 746

Text #17

Max Range: 1.4461. Min Range: -1.4461

Max Act: 0.9724. Min Act: -0.0000

Data Index: 1117418 (C4 (Web Text))

Max Activating Token Index: 664

Text #18

Max Range: 1.4461. Min Range: -1.4461

Max Act: 1.0315. Min Act: -0.0000

Data Index: 302451 (C4 (Web Text))

Max Activating Token Index: 413

Text #19

Max Range: 1.4461. Min Range: -1.4461

Max Act: 1.0882. Min Act: -0.0000

Data Index: 562776 (C4 (Web Text))

Max Activating Token Index: 586