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

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

Neuron 2637 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9958. Min Range: -2.9958

Max Act: 2.9958. Min Act: -0.0000

Data Index: 159720 (C4 (Web Text))

Max Activating Token Index: 891

Text #1

Max Range: 2.9958. Min Range: -2.9958

Max Act: 2.5029. Min Act: -0.0000

Data Index: 82779 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 2.9958. Min Range: -2.9958

Max Act: 2.6350. Min Act: -0.0000

Data Index: 484900 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 2.9958. Min Range: -2.9958

Max Act: 2.7653. Min Act: -0.0000

Data Index: 333496 (C4 (Web Text))

Max Activating Token Index: 196

Text #4

Max Range: 2.9958. Min Range: -2.9958

Max Act: 2.5221. Min Act: -0.0000

Data Index: 335080 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 2.9958. Min Range: -2.9958

Max Act: 2.2933. Min Act: -0.0000

Data Index: 776128 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 2.9958. Min Range: -2.9958

Max Act: 2.2939. Min Act: -0.0000

Data Index: 300157 (C4 (Web Text))

Max Activating Token Index: 529

Text #7

Max Range: 2.9958. Min Range: -2.9958

Max Act: 2.4069. Min Act: -0.0000

Data Index: 1057738 (C4 (Web Text))

Max Activating Token Index: 440

Text #8

Max Range: 2.9958. Min Range: -2.9958

Max Act: 2.6486. Min Act: -0.0000

Data Index: 481455 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 2.9958. Min Range: -2.9958

Max Act: 2.2633. Min Act: -0.0000

Data Index: 655186 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 2.9958. Min Range: -2.9958

Max Act: 2.3785. Min Act: -0.0000

Data Index: 156282 (C4 (Web Text))

Max Activating Token Index: 291

Text #11

Max Range: 2.9958. Min Range: -2.9958

Max Act: 2.3431. Min Act: -0.0000

Data Index: 1253854 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 2.9958. Min Range: -2.9958

Max Act: 2.2555. Min Act: -0.0000

Data Index: 979650 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 2.9958. Min Range: -2.9958

Max Act: 2.1213. Min Act: -0.0000

Data Index: 1006325 (C4 (Web Text))

Max Activating Token Index: 551

Text #14

Max Range: 2.9958. Min Range: -2.9958

Max Act: 2.1847. Min Act: -0.0000

Data Index: 1059825 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 2.9958. Min Range: -2.9958

Max Act: 2.0724. Min Act: -0.0000

Data Index: 966140 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 2.9958. Min Range: -2.9958

Max Act: 2.0681. Min Act: -0.0000

Data Index: 44757 (C4 (Web Text))

Max Activating Token Index: 409

Text #17

Max Range: 2.9958. Min Range: -2.9958

Max Act: 2.1482. Min Act: -0.0000

Data Index: 210905 (C4 (Web Text))

Max Activating Token Index: 721

Text #18

Max Range: 2.9958. Min Range: -2.9958

Max Act: 2.0495. Min Act: -0.0000

Data Index: 892383 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 2.9958. Min Range: -2.9958

Max Act: 2.0054. Min Act: -0.0000

Data Index: 391984 (C4 (Web Text))

Max Activating Token Index: 299