Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3779 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0519. Min Act: -0.0002

Data Index: 1398662 (Python Code)

Max Activating Token Index: 876

Text #1

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0486. Min Act: -0.0002

Data Index: 1509756 (Python Code)

Max Activating Token Index: 616

Text #2

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1580053 (Python Code)

Max Activating Token Index: 160

Text #3

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0472. Min Act: -0.0002

Data Index: 1623175 (Python Code)

Max Activating Token Index: 786

Text #4

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0452. Min Act: -0.0002

Data Index: 1479136 (Python Code)

Max Activating Token Index: 65

Text #5

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0424. Min Act: -0.0003

Data Index: 669177 (C4 (Web Text))

Max Activating Token Index: 167

Text #6

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0376. Min Act: -0.0002

Data Index: 1419317 (Python Code)

Max Activating Token Index: 973

Text #7

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0360. Min Act: -0.0002

Data Index: 1567276 (Python Code)

Max Activating Token Index: 904

Text #8

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0358. Min Act: -0.0002

Data Index: 180773 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0357. Min Act: -0.0003

Data Index: 1045104 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0340. Min Act: -0.0003

Data Index: 445625 (C4 (Web Text))

Max Activating Token Index: 836

Text #11

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0332. Min Act: -0.0002

Data Index: 1642165 (Python Code)

Max Activating Token Index: 787

Text #12

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0340. Min Act: -0.0003

Data Index: 365742 (C4 (Web Text))

Max Activating Token Index: 186

Text #13

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0332. Min Act: -0.0002

Data Index: 1577825 (Python Code)

Max Activating Token Index: 910

Text #14

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0330. Min Act: -0.0003

Data Index: 730045 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0329. Min Act: -0.0003

Data Index: 1355700 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0326. Min Act: -0.0003

Data Index: 885282 (C4 (Web Text))

Max Activating Token Index: 324

Text #17

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0326. Min Act: -0.0003

Data Index: 153017 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0332. Min Act: -0.0002

Data Index: 1633911 (Python Code)

Max Activating Token Index: 725

Text #19

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0324. Min Act: -0.0002

Data Index: 696589 (C4 (Web Text))

Max Activating Token Index: 537