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

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

Neuron 4820 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0594. Min Act: -0.0002

Data Index: 328747 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0527. Min Act: -0.0002

Data Index: 494087 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0537. Min Act: -0.0002

Data Index: 209947 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0482. Min Act: -0.0002

Data Index: 97016 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0469. Min Act: -0.0002

Data Index: 275498 (C4 (Web Text))

Max Activating Token Index: 502

Text #5

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0429. Min Act: -0.0002

Data Index: 24884 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0405. Min Act: -0.0002

Data Index: 152585 (C4 (Web Text))

Max Activating Token Index: 294

Text #7

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0422. Min Act: -0.0002

Data Index: 1316927 (C4 (Web Text))

Max Activating Token Index: 887

Text #8

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0394. Min Act: -0.0002

Data Index: 726963 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0389. Min Act: -0.0002

Data Index: 863654 (C4 (Web Text))

Max Activating Token Index: 53

Text #10

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0373. Min Act: -0.0002

Data Index: 596072 (C4 (Web Text))

Max Activating Token Index: 351

Text #11

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0376. Min Act: -0.0002

Data Index: 190932 (C4 (Web Text))

Max Activating Token Index: 494

Text #12

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0360. Min Act: -0.0002

Data Index: 379133 (C4 (Web Text))

Max Activating Token Index: 425

Text #13

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0360. Min Act: -0.0002

Data Index: 1239406 (C4 (Web Text))

Max Activating Token Index: 120

Text #14

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0365. Min Act: -0.0002

Data Index: 1144417 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0365. Min Act: -0.0002

Data Index: 1037464 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0358. Min Act: -0.0002

Data Index: 626792 (C4 (Web Text))

Max Activating Token Index: 102

Text #17

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0346. Min Act: -0.0002

Data Index: 902044 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0359. Min Act: -0.0002

Data Index: 1066453 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0343. Min Act: -0.0002

Data Index: 941672 (C4 (Web Text))

Max Activating Token Index: 946