Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1873 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0451. Min Act: -0.0003

Data Index: 1578433 (Python Code)

Max Activating Token Index: 517

Text #1

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0409. Min Act: -0.0003

Data Index: 70611 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0389. Min Act: -0.0003

Data Index: 1403309 (Python Code)

Max Activating Token Index: 848

Text #3

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0403. Min Act: -0.0003

Data Index: 1228153 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0360. Min Act: -0.0003

Data Index: 998326 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0365. Min Act: -0.0003

Data Index: 362560 (C4 (Web Text))

Max Activating Token Index: 214

Text #6

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0360. Min Act: -0.0003

Data Index: 1499448 (Python Code)

Max Activating Token Index: 719

Text #7

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0368. Min Act: -0.0003

Data Index: 998723 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0360. Min Act: -0.0002

Data Index: 849938 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0338. Min Act: -0.0002

Data Index: 1127490 (C4 (Web Text))

Max Activating Token Index: 726

Text #10

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0346. Min Act: -0.0002

Data Index: 213008 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0346. Min Act: -0.0003

Data Index: 1197628 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0342. Min Act: -0.0003

Data Index: 1205223 (C4 (Web Text))

Max Activating Token Index: 558

Text #13

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0340. Min Act: -0.0003

Data Index: 1308241 (C4 (Web Text))

Max Activating Token Index: 965

Text #14

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0355. Min Act: -0.0002

Data Index: 1129512 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0334. Min Act: -0.0003

Data Index: 749806 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0332. Min Act: -0.0002

Data Index: 760407 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0330. Min Act: -0.0002

Data Index: 1524000 (Python Code)

Max Activating Token Index: 567

Text #18

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0322. Min Act: -0.0003

Data Index: 756987 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0320. Min Act: -0.0002

Data Index: 1628762 (Python Code)

Max Activating Token Index: 844