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

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

Neuron 2343 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5200. Min Range: -1.5200

Max Act: 1.4435. Min Act: -0.0001

Data Index: 1275926 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 1.5200. Min Range: -1.5200

Max Act: 1.4966. Min Act: -0.0001

Data Index: 401161 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 1.5200. Min Range: -1.5200

Max Act: 1.5200. Min Act: -0.0001

Data Index: 757559 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 1.5200. Min Range: -1.5200

Max Act: 1.3312. Min Act: -0.0001

Data Index: 353916 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 1.5200. Min Range: -1.5200

Max Act: 1.2551. Min Act: -0.0001

Data Index: 23277 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 1.5200. Min Range: -1.5200

Max Act: 1.0749. Min Act: -0.0001

Data Index: 1231914 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 1.5200. Min Range: -1.5200

Max Act: 0.9520. Min Act: -0.0001

Data Index: 633267 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 1.5200. Min Range: -1.5200

Max Act: 0.9751. Min Act: -0.0001

Data Index: 572243 (C4 (Web Text))

Max Activating Token Index: 955

Text #8

Max Range: 1.5200. Min Range: -1.5200

Max Act: 1.0053. Min Act: -0.0001

Data Index: 992623 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 1.5200. Min Range: -1.5200

Max Act: 0.9606. Min Act: -0.0001

Data Index: 626424 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 1.5200. Min Range: -1.5200

Max Act: 0.9600. Min Act: -0.0001

Data Index: 1079515 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 1.5200. Min Range: -1.5200

Max Act: 0.8959. Min Act: -0.0001

Data Index: 883037 (C4 (Web Text))

Max Activating Token Index: 165

Text #12

Max Range: 1.5200. Min Range: -1.5200

Max Act: 1.0315. Min Act: -0.0001

Data Index: 49455 (C4 (Web Text))

Max Activating Token Index: 829

Text #13

Max Range: 1.5200. Min Range: -1.5200

Max Act: 0.8754. Min Act: -0.0001

Data Index: 453642 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 1.5200. Min Range: -1.5200

Max Act: 0.8744. Min Act: -0.0001

Data Index: 59428 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 1.5200. Min Range: -1.5200

Max Act: 0.7756. Min Act: -0.0001

Data Index: 1107876 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 1.5200. Min Range: -1.5200

Max Act: 0.8262. Min Act: -0.0001

Data Index: 1084788 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 1.5200. Min Range: -1.5200

Max Act: 0.9172. Min Act: -0.0001

Data Index: 155487 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 1.5200. Min Range: -1.5200

Max Act: 0.8564. Min Act: -0.0001

Data Index: 765513 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 1.5200. Min Range: -1.5200

Max Act: 0.7639. Min Act: -0.0001

Data Index: 585304 (C4 (Web Text))

Max Activating Token Index: 507