Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4165 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.5072. Min Act: -0.0000

Data Index: 577238 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4496. Min Act: -0.0000

Data Index: 81740 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4068. Min Act: -0.0000

Data Index: 90055 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3403. Min Act: -0.0000

Data Index: 481231 (C4 (Web Text))

Max Activating Token Index: 599

Text #4

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3329. Min Act: -0.0000

Data Index: 63488 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3346. Min Act: -0.0000

Data Index: 548213 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3202. Min Act: -0.0000

Data Index: 1101435 (C4 (Web Text))

Max Activating Token Index: 275

Text #7

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3480. Min Act: -0.0000

Data Index: 1172248 (C4 (Web Text))

Max Activating Token Index: 470

Text #8

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3150. Min Act: -0.0000

Data Index: 815729 (C4 (Web Text))

Max Activating Token Index: 643

Text #9

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3396. Min Act: -0.0000

Data Index: 845304 (C4 (Web Text))

Max Activating Token Index: 230

Text #10

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3158. Min Act: -0.0000

Data Index: 1305064 (C4 (Web Text))

Max Activating Token Index: 397

Text #11

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3219. Min Act: -0.0000

Data Index: 1112460 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.2942. Min Act: -0.0000

Data Index: 424201 (C4 (Web Text))

Max Activating Token Index: 324

Text #13

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3309. Min Act: -0.0000

Data Index: 1580836 (Python Code)

Max Activating Token Index: 817

Text #14

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3030. Min Act: -0.0000

Data Index: 1333434 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.2996. Min Act: -0.0000

Data Index: 422402 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3192. Min Act: -0.0000

Data Index: 1401658 (Python Code)

Max Activating Token Index: 411

Text #17

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3230. Min Act: -0.0000

Data Index: 221144 (C4 (Web Text))

Max Activating Token Index: 755

Text #18

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3045. Min Act: -0.0000

Data Index: 1593569 (Python Code)

Max Activating Token Index: 933

Text #19

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3210. Min Act: -0.0000

Data Index: 98285 (C4 (Web Text))

Max Activating Token Index: 230