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

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

Neuron 647 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.3037. Min Act: -0.0002

Data Index: 36896 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2893. Min Act: -0.0002

Data Index: 1165008 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2896. Min Act: -0.0002

Data Index: 1234622 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2824. Min Act: -0.0002

Data Index: 370258 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2767. Min Act: -0.0002

Data Index: 1063847 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2750. Min Act: -0.0002

Data Index: 820119 (C4 (Web Text))

Max Activating Token Index: 220

Text #6

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2670. Min Act: -0.0002

Data Index: 147946 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2752. Min Act: -0.0002

Data Index: 1112042 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2744. Min Act: -0.0002

Data Index: 470439 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2501. Min Act: -0.0002

Data Index: 307371 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2646. Min Act: -0.0002

Data Index: 280789 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2650. Min Act: -0.0002

Data Index: 1244730 (C4 (Web Text))

Max Activating Token Index: 989

Text #12

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2455. Min Act: -0.0002

Data Index: 864602 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2379. Min Act: -0.0002

Data Index: 83282 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2437. Min Act: -0.0002

Data Index: 577024 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2399. Min Act: -0.0002

Data Index: 708993 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2389. Min Act: -0.0002

Data Index: 689922 (C4 (Web Text))

Max Activating Token Index: 242

Text #17

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2282. Min Act: -0.0002

Data Index: 13588 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2225. Min Act: -0.0002

Data Index: 377804 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 0.3037. Min Range: -0.3037

Max Act: 0.2276. Min Act: -0.0002

Data Index: 1151885 (C4 (Web Text))

Max Activating Token Index: 656