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

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

Neuron 3875 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3338. Min Range: -4.3338

Max Act: 4.2345. Min Act: -0.0000

Data Index: 987049 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 4.3338. Min Range: -4.3338

Max Act: 4.0365. Min Act: -0.0000

Data Index: 187319 (C4 (Web Text))

Max Activating Token Index: 529

Text #2

Max Range: 4.3338. Min Range: -4.3338

Max Act: 4.3338. Min Act: -0.0000

Data Index: 923711 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 4.3338. Min Range: -4.3338

Max Act: 4.0826. Min Act: -0.0000

Data Index: 1323120 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 4.3338. Min Range: -4.3338

Max Act: 3.9270. Min Act: -0.0000

Data Index: 549347 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 4.3338. Min Range: -4.3338

Max Act: 3.6799. Min Act: -0.0000

Data Index: 204854 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 4.3338. Min Range: -4.3338

Max Act: 3.5272. Min Act: -0.0000

Data Index: 985597 (C4 (Web Text))

Max Activating Token Index: 978

Text #7

Max Range: 4.3338. Min Range: -4.3338

Max Act: 3.6727. Min Act: -0.0000

Data Index: 1321820 (C4 (Web Text))

Max Activating Token Index: 798

Text #8

Max Range: 4.3338. Min Range: -4.3338

Max Act: 3.6366. Min Act: -0.0000

Data Index: 71279 (C4 (Web Text))

Max Activating Token Index: 531

Text #9

Max Range: 4.3338. Min Range: -4.3338

Max Act: 3.3302. Min Act: -0.0000

Data Index: 759963 (C4 (Web Text))

Max Activating Token Index: 657

Text #10

Max Range: 4.3338. Min Range: -4.3338

Max Act: 3.4993. Min Act: -0.0000

Data Index: 772828 (C4 (Web Text))

Max Activating Token Index: 168

Text #11

Max Range: 4.3338. Min Range: -4.3338

Max Act: 3.4781. Min Act: -0.0000

Data Index: 823503 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 4.3338. Min Range: -4.3338

Max Act: 3.2723. Min Act: -0.0000

Data Index: 1227217 (C4 (Web Text))

Max Activating Token Index: 938

Text #13

Max Range: 4.3338. Min Range: -4.3338

Max Act: 3.5072. Min Act: -0.0000

Data Index: 784458 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 4.3338. Min Range: -4.3338

Max Act: 3.5089. Min Act: -0.0000

Data Index: 321611 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 4.3338. Min Range: -4.3338

Max Act: 3.3184. Min Act: -0.0000

Data Index: 736864 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 4.3338. Min Range: -4.3338

Max Act: 3.1365. Min Act: -0.0000

Data Index: 262045 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 4.3338. Min Range: -4.3338

Max Act: 3.2938. Min Act: -0.0000

Data Index: 1055654 (C4 (Web Text))

Max Activating Token Index: 431

Text #18

Max Range: 4.3338. Min Range: -4.3338

Max Act: 3.4238. Min Act: -0.0000

Data Index: 1318237 (C4 (Web Text))

Max Activating Token Index: 869

Text #19

Max Range: 4.3338. Min Range: -4.3338

Max Act: 3.2401. Min Act: -0.0000

Data Index: 540441 (C4 (Web Text))

Max Activating Token Index: 877