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

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

Neuron 4788 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: 0.2596. Min Range: -0.2596

Max Act: 0.2596. Min Act: -0.0000

Data Index: 1352701 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2556. Min Act: -0.0000

Data Index: 641780 (C4 (Web Text))

Max Activating Token Index: 821

Text #2

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2439. Min Act: -0.0000

Data Index: 38438 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2400. Min Act: -0.0000

Data Index: 569959 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2377. Min Act: -0.0000

Data Index: 138080 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2435. Min Act: -0.0000

Data Index: 1321876 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2313. Min Act: -0.0000

Data Index: 991318 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2374. Min Act: -0.0000

Data Index: 161896 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2257. Min Act: -0.0000

Data Index: 921972 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2190. Min Act: -0.0000

Data Index: 1229671 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2242. Min Act: -0.0000

Data Index: 589852 (C4 (Web Text))

Max Activating Token Index: 259

Text #11

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2205. Min Act: -0.0000

Data Index: 577513 (C4 (Web Text))

Max Activating Token Index: 501

Text #12

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2467. Min Act: -0.0000

Data Index: 123404 (C4 (Web Text))

Max Activating Token Index: 416

Text #13

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2098. Min Act: -0.0000

Data Index: 895258 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2016. Min Act: -0.0000

Data Index: 1630239 (Python Code)

Max Activating Token Index: 141

Text #15

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.2233. Min Act: -0.0000

Data Index: 1449434 (Python Code)

Max Activating Token Index: 332

Text #16

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.1996. Min Act: -0.0000

Data Index: 928423 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.1978. Min Act: -0.0000

Data Index: 1114135 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.1896. Min Act: -0.0000

Data Index: 554054 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 0.2596. Min Range: -0.2596

Max Act: 0.1957. Min Act: -0.0000

Data Index: 1274097 (C4 (Web Text))

Max Activating Token Index: 480