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

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

Neuron 3713 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.6915. Min Range: -2.6915

Max Act: 2.6915. Min Act: -0.0000

Data Index: 429437 (C4 (Web Text))

Max Activating Token Index: 721

Text #1

Max Range: 2.6915. Min Range: -2.6915

Max Act: 2.6119. Min Act: -0.0000

Data Index: 1359790 (C4 (Web Text))

Max Activating Token Index: 776

Text #2

Max Range: 2.6915. Min Range: -2.6915

Max Act: 2.4686. Min Act: -0.0000

Data Index: 568054 (C4 (Web Text))

Max Activating Token Index: 303

Text #3

Max Range: 2.6915. Min Range: -2.6915

Max Act: 2.2728. Min Act: -0.0000

Data Index: 1200516 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 2.6915. Min Range: -2.6915

Max Act: 2.3698. Min Act: -0.0000

Data Index: 1107015 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 2.6915. Min Range: -2.6915

Max Act: 2.2392. Min Act: -0.0000

Data Index: 546361 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 2.6915. Min Range: -2.6915

Max Act: 2.0595. Min Act: -0.0000

Data Index: 973773 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 2.6915. Min Range: -2.6915

Max Act: 1.7726. Min Act: -0.0000

Data Index: 50220 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 2.6915. Min Range: -2.6915

Max Act: 1.7773. Min Act: -0.0000

Data Index: 1008195 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 2.6915. Min Range: -2.6915

Max Act: 1.8578. Min Act: -0.0000

Data Index: 185504 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 2.6915. Min Range: -2.6915

Max Act: 1.7921. Min Act: -0.0000

Data Index: 1127092 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 2.6915. Min Range: -2.6915

Max Act: 1.7315. Min Act: -0.0000

Data Index: 157975 (C4 (Web Text))

Max Activating Token Index: 828

Text #12

Max Range: 2.6915. Min Range: -2.6915

Max Act: 1.7169. Min Act: -0.0000

Data Index: 344413 (C4 (Web Text))

Max Activating Token Index: 554

Text #13

Max Range: 2.6915. Min Range: -2.6915

Max Act: 1.6070. Min Act: -0.0000

Data Index: 1298500 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 2.6915. Min Range: -2.6915

Max Act: 1.9790. Min Act: -0.0000

Data Index: 799089 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 2.6915. Min Range: -2.6915

Max Act: 1.6894. Min Act: -0.0000

Data Index: 364574 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 2.6915. Min Range: -2.6915

Max Act: 1.5868. Min Act: -0.0000

Data Index: 459510 (C4 (Web Text))

Max Activating Token Index: 515

Text #17

Max Range: 2.6915. Min Range: -2.6915

Max Act: 1.6425. Min Act: -0.0000

Data Index: 618711 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 2.6915. Min Range: -2.6915

Max Act: 1.6352. Min Act: -0.0000

Data Index: 1113279 (C4 (Web Text))

Max Activating Token Index: 983

Text #19

Max Range: 2.6915. Min Range: -2.6915

Max Act: 1.6502. Min Act: -0.0000

Data Index: 261904 (C4 (Web Text))

Max Activating Token Index: 218