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

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

Neuron 3243 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3615. Min Act: -0.0002

Data Index: 1346230 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3623. Min Act: -0.0003

Data Index: 807709 (C4 (Web Text))

Max Activating Token Index: 606

Text #2

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3521. Min Act: -0.0002

Data Index: 731907 (C4 (Web Text))

Max Activating Token Index: 661

Text #3

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3587. Min Act: -0.0002

Data Index: 685484 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3467. Min Act: -0.0002

Data Index: 50141 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3420. Min Act: -0.0002

Data Index: 36293 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3249. Min Act: -0.0002

Data Index: 699258 (C4 (Web Text))

Max Activating Token Index: 386

Text #7

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3462. Min Act: -0.0002

Data Index: 614512 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3228. Min Act: -0.0003

Data Index: 280471 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3325. Min Act: -0.0002

Data Index: 1354048 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3382. Min Act: -0.0003

Data Index: 526704 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3380. Min Act: -0.0003

Data Index: 540211 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3265. Min Act: -0.0002

Data Index: 1174192 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3380. Min Act: -0.0002

Data Index: 621743 (C4 (Web Text))

Max Activating Token Index: 628

Text #14

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3358. Min Act: -0.0003

Data Index: 625011 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3117. Min Act: -0.0002

Data Index: 683653 (C4 (Web Text))

Max Activating Token Index: 869

Text #16

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3094. Min Act: -0.0002

Data Index: 1117934 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3169. Min Act: -0.0002

Data Index: 266349 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3246. Min Act: -0.0002

Data Index: 967954 (C4 (Web Text))

Max Activating Token Index: 554

Text #19

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3135. Min Act: -0.0002

Data Index: 1146983 (C4 (Web Text))

Max Activating Token Index: 952