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

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

Neuron 1606 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.2601. Min Act: -0.0002

Data Index: 702624 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.2374. Min Act: -0.0002

Data Index: 350309 (C4 (Web Text))

Max Activating Token Index: 622

Text #2

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.2429. Min Act: -0.0002

Data Index: 50239 (C4 (Web Text))

Max Activating Token Index: 289

Text #3

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.2262. Min Act: -0.0002

Data Index: 668716 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.2243. Min Act: -0.0002

Data Index: 828041 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.2231. Min Act: -0.0002

Data Index: 138910 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.2224. Min Act: -0.0002

Data Index: 215525 (C4 (Web Text))

Max Activating Token Index: 529

Text #7

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.2303. Min Act: -0.0002

Data Index: 826846 (C4 (Web Text))

Max Activating Token Index: 548

Text #8

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.2117. Min Act: -0.0002

Data Index: 671966 (C4 (Web Text))

Max Activating Token Index: 455

Text #9

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.2200. Min Act: -0.0002

Data Index: 365983 (C4 (Web Text))

Max Activating Token Index: 531

Text #10

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.2187. Min Act: -0.0002

Data Index: 40855 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.2054. Min Act: -0.0002

Data Index: 703428 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.2102. Min Act: -0.0002

Data Index: 1322690 (C4 (Web Text))

Max Activating Token Index: 542

Text #13

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.2039. Min Act: -0.0002

Data Index: 391711 (C4 (Web Text))

Max Activating Token Index: 335

Text #14

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.2116. Min Act: -0.0002

Data Index: 414748 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.2220. Min Act: -0.0002

Data Index: 1227062 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.2069. Min Act: -0.0002

Data Index: 1012138 (C4 (Web Text))

Max Activating Token Index: 803

Text #17

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1891. Min Act: -0.0002

Data Index: 546954 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1884. Min Act: -0.0002

Data Index: 251519 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 0.2601. Min Range: -0.2601

Max Act: 0.1936. Min Act: -0.0002

Data Index: 729424 (C4 (Web Text))

Max Activating Token Index: 42