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

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

Neuron 4760 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: 2.0393. Min Range: -2.0393

Max Act: 2.0393. Min Act: -0.0000

Data Index: 1131458 (C4 (Web Text))

Max Activating Token Index: 202

Text #1

Max Range: 2.0393. Min Range: -2.0393

Max Act: 1.9755. Min Act: -0.0000

Data Index: 853947 (C4 (Web Text))

Max Activating Token Index: 415

Text #2

Max Range: 2.0393. Min Range: -2.0393

Max Act: 1.6870. Min Act: -0.0000

Data Index: 1275642 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 2.0393. Min Range: -2.0393

Max Act: 1.7094. Min Act: -0.0000

Data Index: 568478 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 2.0393. Min Range: -2.0393

Max Act: 1.5746. Min Act: -0.0000

Data Index: 699709 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 2.0393. Min Range: -2.0393

Max Act: 1.4655. Min Act: -0.0000

Data Index: 1316397 (C4 (Web Text))

Max Activating Token Index: 549

Text #6

Max Range: 2.0393. Min Range: -2.0393

Max Act: 1.5394. Min Act: -0.0000

Data Index: 448182 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 2.0393. Min Range: -2.0393

Max Act: 1.5179. Min Act: -0.0000

Data Index: 551633 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 2.0393. Min Range: -2.0393

Max Act: 1.4160. Min Act: -0.0000

Data Index: 362989 (C4 (Web Text))

Max Activating Token Index: 626

Text #9

Max Range: 2.0393. Min Range: -2.0393

Max Act: 1.3383. Min Act: -0.0000

Data Index: 246996 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 2.0393. Min Range: -2.0393

Max Act: 1.2953. Min Act: -0.0000

Data Index: 189131 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 2.0393. Min Range: -2.0393

Max Act: 1.3219. Min Act: -0.0000

Data Index: 880193 (C4 (Web Text))

Max Activating Token Index: 958

Text #12

Max Range: 2.0393. Min Range: -2.0393

Max Act: 1.3144. Min Act: -0.0000

Data Index: 504318 (C4 (Web Text))

Max Activating Token Index: 645

Text #13

Max Range: 2.0393. Min Range: -2.0393

Max Act: 1.5587. Min Act: -0.0000

Data Index: 594524 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 2.0393. Min Range: -2.0393

Max Act: 1.4620. Min Act: -0.0000

Data Index: 1235793 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 2.0393. Min Range: -2.0393

Max Act: 1.3701. Min Act: -0.0000

Data Index: 1539001 (Python Code)

Max Activating Token Index: 155

Text #16

Max Range: 2.0393. Min Range: -2.0393

Max Act: 1.2783. Min Act: -0.0000

Data Index: 730128 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 2.0393. Min Range: -2.0393

Max Act: 1.3681. Min Act: -0.0000

Data Index: 1014323 (C4 (Web Text))

Max Activating Token Index: 1002

Text #18

Max Range: 2.0393. Min Range: -2.0393

Max Act: 1.3684. Min Act: -0.0000

Data Index: 374063 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 2.0393. Min Range: -2.0393

Max Act: 1.3479. Min Act: -0.0000

Data Index: 677022 (C4 (Web Text))

Max Activating Token Index: 90