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

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

Neuron 422 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0409. Min Range: -3.0409

Max Act: 3.0409. Min Act: -0.0000

Data Index: 695650 (C4 (Web Text))

Max Activating Token Index: 190

Text #1

Max Range: 3.0409. Min Range: -3.0409

Max Act: 2.9104. Min Act: -0.0000

Data Index: 268783 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 3.0409. Min Range: -3.0409

Max Act: 3.0118. Min Act: -0.0000

Data Index: 1099461 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 3.0409. Min Range: -3.0409

Max Act: 2.7669. Min Act: -0.0000

Data Index: 195844 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 3.0409. Min Range: -3.0409

Max Act: 2.7246. Min Act: -0.0000

Data Index: 379190 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 3.0409. Min Range: -3.0409

Max Act: 2.7982. Min Act: -0.0000

Data Index: 461559 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 3.0409. Min Range: -3.0409

Max Act: 2.8116. Min Act: -0.0000

Data Index: 1282518 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 3.0409. Min Range: -3.0409

Max Act: 2.6339. Min Act: -0.0000

Data Index: 339191 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 3.0409. Min Range: -3.0409

Max Act: 2.5961. Min Act: -0.0000

Data Index: 421221 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 3.0409. Min Range: -3.0409

Max Act: 2.7197. Min Act: -0.0000

Data Index: 142914 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 3.0409. Min Range: -3.0409

Max Act: 2.5486. Min Act: -0.0000

Data Index: 1341073 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 3.0409. Min Range: -3.0409

Max Act: 2.4731. Min Act: -0.0000

Data Index: 1044667 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 3.0409. Min Range: -3.0409

Max Act: 2.4505. Min Act: -0.0000

Data Index: 247950 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 3.0409. Min Range: -3.0409

Max Act: 2.3254. Min Act: -0.0000

Data Index: 400333 (C4 (Web Text))

Max Activating Token Index: 142

Text #14

Max Range: 3.0409. Min Range: -3.0409

Max Act: 2.5669. Min Act: -0.0000

Data Index: 1210592 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 3.0409. Min Range: -3.0409

Max Act: 2.4382. Min Act: -0.0000

Data Index: 901306 (C4 (Web Text))

Max Activating Token Index: 7

Text #16

Max Range: 3.0409. Min Range: -3.0409

Max Act: 2.4160. Min Act: -0.0000

Data Index: 573589 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 3.0409. Min Range: -3.0409

Max Act: 2.5306. Min Act: -0.0000

Data Index: 15757 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 3.0409. Min Range: -3.0409

Max Act: 2.2742. Min Act: -0.0000

Data Index: 753974 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 3.0409. Min Range: -3.0409

Max Act: 2.4962. Min Act: -0.0000

Data Index: 948185 (C4 (Web Text))

Max Activating Token Index: 244