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

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

Neuron 3051 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: 0.4103. Min Range: -0.4103

Max Act: 0.4103. Min Act: -0.0000

Data Index: 196739 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3916. Min Act: -0.0000

Data Index: 223370 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3681. Min Act: -0.0000

Data Index: 1351373 (C4 (Web Text))

Max Activating Token Index: 604

Text #3

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3688. Min Act: -0.0000

Data Index: 807317 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3908. Min Act: -0.0000

Data Index: 1250995 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3469. Min Act: -0.0000

Data Index: 817847 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3506. Min Act: -0.0000

Data Index: 1208696 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3432. Min Act: -0.0000

Data Index: 359344 (C4 (Web Text))

Max Activating Token Index: 40

Text #8

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3259. Min Act: -0.0000

Data Index: 122952 (C4 (Web Text))

Max Activating Token Index: 548

Text #9

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3414. Min Act: -0.0000

Data Index: 279092 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3152. Min Act: -0.0000

Data Index: 924163 (C4 (Web Text))

Max Activating Token Index: 270

Text #11

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3171. Min Act: -0.0000

Data Index: 114980 (C4 (Web Text))

Max Activating Token Index: 750

Text #12

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3413. Min Act: -0.0000

Data Index: 908430 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3256. Min Act: -0.0000

Data Index: 748204 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3269. Min Act: -0.0000

Data Index: 974076 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3207. Min Act: -0.0000

Data Index: 747440 (C4 (Web Text))

Max Activating Token Index: 613

Text #16

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3212. Min Act: -0.0000

Data Index: 598666 (C4 (Web Text))

Max Activating Token Index: 528

Text #17

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3308. Min Act: -0.0000

Data Index: 1131534 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3300. Min Act: -0.0000

Data Index: 599071 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.2933. Min Act: -0.0000

Data Index: 259340 (C4 (Web Text))

Max Activating Token Index: 318