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

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

Neuron 5441 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: 0.2999. Min Range: -0.2999

Max Act: 0.2695. Min Act: -0.0000

Data Index: 641960 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 0.2999. Min Range: -0.2999

Max Act: 0.2665. Min Act: -0.0000

Data Index: 105905 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 0.2999. Min Range: -0.2999

Max Act: 0.2753. Min Act: -0.0000

Data Index: 643249 (C4 (Web Text))

Max Activating Token Index: 740

Text #3

Max Range: 0.2999. Min Range: -0.2999

Max Act: 0.2544. Min Act: -0.0000

Data Index: 176578 (C4 (Web Text))

Max Activating Token Index: 84

Text #4

Max Range: 0.2999. Min Range: -0.2999

Max Act: 0.2439. Min Act: -0.0000

Data Index: 612717 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 0.2999. Min Range: -0.2999

Max Act: 0.2618. Min Act: -0.0000

Data Index: 1057703 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 0.2999. Min Range: -0.2999

Max Act: 0.2477. Min Act: -0.0000

Data Index: 777548 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 0.2999. Min Range: -0.2999

Max Act: 0.2459. Min Act: -0.0000

Data Index: 10167 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 0.2999. Min Range: -0.2999

Max Act: 0.2999. Min Act: -0.0000

Data Index: 1316471 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 0.2999. Min Range: -0.2999

Max Act: 0.2209. Min Act: -0.0000

Data Index: 878086 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 0.2999. Min Range: -0.2999

Max Act: 0.2312. Min Act: -0.0000

Data Index: 790373 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 0.2999. Min Range: -0.2999

Max Act: 0.2520. Min Act: -0.0000

Data Index: 600282 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 0.2999. Min Range: -0.2999

Max Act: 0.2239. Min Act: -0.0000

Data Index: 850096 (C4 (Web Text))

Max Activating Token Index: 499

Text #13

Max Range: 0.2999. Min Range: -0.2999

Max Act: 0.2297. Min Act: -0.0000

Data Index: 1002373 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 0.2999. Min Range: -0.2999

Max Act: 0.2208. Min Act: -0.0000

Data Index: 497662 (C4 (Web Text))

Max Activating Token Index: 946

Text #15

Max Range: 0.2999. Min Range: -0.2999

Max Act: 0.2274. Min Act: -0.0000

Data Index: 584877 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 0.2999. Min Range: -0.2999

Max Act: 0.2346. Min Act: -0.0000

Data Index: 218994 (C4 (Web Text))

Max Activating Token Index: 191

Text #17

Max Range: 0.2999. Min Range: -0.2999

Max Act: 0.2238. Min Act: -0.0000

Data Index: 916495 (C4 (Web Text))

Max Activating Token Index: 962

Text #18

Max Range: 0.2999. Min Range: -0.2999

Max Act: 0.2028. Min Act: -0.0000

Data Index: 462271 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 0.2999. Min Range: -0.2999

Max Act: 0.1877. Min Act: -0.0000

Data Index: 387451 (C4 (Web Text))

Max Activating Token Index: 339