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

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

Neuron 4778 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: 6.0098. Min Range: -6.0098

Max Act: 6.0098. Min Act: -0.0000

Data Index: 195241 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 6.0098. Min Range: -6.0098

Max Act: 5.5953. Min Act: -0.0000

Data Index: 504873 (C4 (Web Text))

Max Activating Token Index: 409

Text #2

Max Range: 6.0098. Min Range: -6.0098

Max Act: 5.5678. Min Act: -0.0000

Data Index: 161383 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 6.0098. Min Range: -6.0098

Max Act: 5.4768. Min Act: -0.0000

Data Index: 506207 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 6.0098. Min Range: -6.0098

Max Act: 5.4255. Min Act: -0.0000

Data Index: 934032 (C4 (Web Text))

Max Activating Token Index: 593

Text #5

Max Range: 6.0098. Min Range: -6.0098

Max Act: 5.3927. Min Act: -0.0000

Data Index: 107121 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 6.0098. Min Range: -6.0098

Max Act: 5.2426. Min Act: -0.0000

Data Index: 244726 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 6.0098. Min Range: -6.0098

Max Act: 4.6049. Min Act: -0.0000

Data Index: 604027 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 6.0098. Min Range: -6.0098

Max Act: 4.9595. Min Act: -0.0000

Data Index: 1029449 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 6.0098. Min Range: -6.0098

Max Act: 4.6047. Min Act: -0.0000

Data Index: 119138 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 6.0098. Min Range: -6.0098

Max Act: 4.8477. Min Act: -0.0000

Data Index: 685380 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 6.0098. Min Range: -6.0098

Max Act: 4.6536. Min Act: -0.0000

Data Index: 1030336 (C4 (Web Text))

Max Activating Token Index: 90

Text #12

Max Range: 6.0098. Min Range: -6.0098

Max Act: 4.4408. Min Act: -0.0000

Data Index: 1116792 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 6.0098. Min Range: -6.0098

Max Act: 4.6069. Min Act: -0.0000

Data Index: 63621 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 6.0098. Min Range: -6.0098

Max Act: 4.5332. Min Act: -0.0001

Data Index: 972091 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 6.0098. Min Range: -6.0098

Max Act: 4.5158. Min Act: -0.0000

Data Index: 289348 (C4 (Web Text))

Max Activating Token Index: 442

Text #16

Max Range: 6.0098. Min Range: -6.0098

Max Act: 4.4350. Min Act: -0.0000

Data Index: 663428 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 6.0098. Min Range: -6.0098

Max Act: 4.4006. Min Act: -0.0000

Data Index: 556848 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 6.0098. Min Range: -6.0098

Max Act: 4.2021. Min Act: -0.0000

Data Index: 199515 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 6.0098. Min Range: -6.0098

Max Act: 4.3737. Min Act: -0.0000

Data Index: 36476 (C4 (Web Text))

Max Activating Token Index: 459