Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4668 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.4461. Min Range: -4.4461

Max Act: 4.1972. Min Act: -0.0000

Data Index: 450874 (C4 (Web Text))

Max Activating Token Index: 562

Text #1

Max Range: 4.4461. Min Range: -4.4461

Max Act: 4.2794. Min Act: -0.0000

Data Index: 797332 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 4.4461. Min Range: -4.4461

Max Act: 4.2164. Min Act: -0.0000

Data Index: 886044 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 4.4461. Min Range: -4.4461

Max Act: 4.4461. Min Act: -0.0000

Data Index: 955438 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 4.4461. Min Range: -4.4461

Max Act: 3.9096. Min Act: -0.0000

Data Index: 448880 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 4.4461. Min Range: -4.4461

Max Act: 4.0630. Min Act: -0.0000

Data Index: 303392 (C4 (Web Text))

Max Activating Token Index: 403

Text #6

Max Range: 4.4461. Min Range: -4.4461

Max Act: 4.0075. Min Act: -0.0000

Data Index: 498993 (C4 (Web Text))

Max Activating Token Index: 953

Text #7

Max Range: 4.4461. Min Range: -4.4461

Max Act: 4.1950. Min Act: -0.0000

Data Index: 416836 (C4 (Web Text))

Max Activating Token Index: 800

Text #8

Max Range: 4.4461. Min Range: -4.4461

Max Act: 3.9794. Min Act: -0.0000

Data Index: 60054 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 4.4461. Min Range: -4.4461

Max Act: 4.1046. Min Act: -0.0000

Data Index: 730457 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 4.4461. Min Range: -4.4461

Max Act: 3.9493. Min Act: -0.0000

Data Index: 328467 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 4.4461. Min Range: -4.4461

Max Act: 4.0456. Min Act: -0.0000

Data Index: 764279 (C4 (Web Text))

Max Activating Token Index: 934

Text #12

Max Range: 4.4461. Min Range: -4.4461

Max Act: 3.8566. Min Act: -0.0000

Data Index: 1213864 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 4.4461. Min Range: -4.4461

Max Act: 3.8451. Min Act: -0.0000

Data Index: 1157292 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 4.4461. Min Range: -4.4461

Max Act: 3.9560. Min Act: -0.0000

Data Index: 110253 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 4.4461. Min Range: -4.4461

Max Act: 3.8016. Min Act: -0.0000

Data Index: 192232 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 4.4461. Min Range: -4.4461

Max Act: 3.7823. Min Act: -0.0000

Data Index: 453735 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 4.4461. Min Range: -4.4461

Max Act: 3.7543. Min Act: -0.0000

Data Index: 301760 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 4.4461. Min Range: -4.4461

Max Act: 3.4931. Min Act: -0.0000

Data Index: 156834 (C4 (Web Text))

Max Activating Token Index: 818

Text #19

Max Range: 4.4461. Min Range: -4.4461

Max Act: 3.6596. Min Act: -0.0000

Data Index: 771186 (C4 (Web Text))

Max Activating Token Index: 965