Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3945 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.4776. Min Act: -0.0000

Data Index: 512844 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.4355. Min Act: -0.0000

Data Index: 212898 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3883. Min Act: -0.0000

Data Index: 676105 (C4 (Web Text))

Max Activating Token Index: 943

Text #3

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.4471. Min Act: -0.0000

Data Index: 1226576 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.4375. Min Act: -0.0000

Data Index: 56577 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.4036. Min Act: -0.0000

Data Index: 548623 (C4 (Web Text))

Max Activating Token Index: 118

Text #6

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.4215. Min Act: -0.0000

Data Index: 1296742 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3859. Min Act: -0.0000

Data Index: 1223886 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.4015. Min Act: -0.0000

Data Index: 429415 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3603. Min Act: -0.0000

Data Index: 427854 (C4 (Web Text))

Max Activating Token Index: 730

Text #10

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3663. Min Act: -0.0000

Data Index: 93554 (C4 (Web Text))

Max Activating Token Index: 513

Text #11

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3436. Min Act: -0.0000

Data Index: 223853 (C4 (Web Text))

Max Activating Token Index: 259

Text #12

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3105. Min Act: -0.0000

Data Index: 657674 (C4 (Web Text))

Max Activating Token Index: 110

Text #13

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3403. Min Act: -0.0000

Data Index: 809517 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3415. Min Act: -0.0000

Data Index: 516700 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3396. Min Act: -0.0000

Data Index: 1097877 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3287. Min Act: -0.0000

Data Index: 409184 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3075. Min Act: -0.0000

Data Index: 632653 (C4 (Web Text))

Max Activating Token Index: 651

Text #18

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3246. Min Act: -0.0000

Data Index: 1296387 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 0.4776. Min Range: -0.4776

Max Act: 0.3248. Min Act: -0.0000

Data Index: 515623 (C4 (Web Text))

Max Activating Token Index: 496