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

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

Neuron 5034 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.5893. Min Act: -0.0000

Data Index: 1137839 (C4 (Web Text))

Max Activating Token Index: 266

Text #1

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.3977. Min Act: -0.0000

Data Index: 438623 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.4723. Min Act: -0.0000

Data Index: 877239 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.5147. Min Act: -0.0000

Data Index: 340509 (C4 (Web Text))

Max Activating Token Index: 460

Text #4

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.4522. Min Act: -0.0000

Data Index: 199674 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.4780. Min Act: -0.0000

Data Index: 415546 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.4566. Min Act: -0.0000

Data Index: 299529 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.4779. Min Act: -0.0000

Data Index: 485701 (C4 (Web Text))

Max Activating Token Index: 568

Text #8

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.4553. Min Act: -0.0000

Data Index: 1242448 (C4 (Web Text))

Max Activating Token Index: 783

Text #9

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.4473. Min Act: -0.0000

Data Index: 259040 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.4639. Min Act: -0.0000

Data Index: 185774 (C4 (Web Text))

Max Activating Token Index: 181

Text #11

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.4379. Min Act: -0.0000

Data Index: 1315166 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.4565. Min Act: -0.0000

Data Index: 1333932 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.4086. Min Act: -0.0000

Data Index: 1193167 (C4 (Web Text))

Max Activating Token Index: 463

Text #14

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.4150. Min Act: -0.0000

Data Index: 943058 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.4134. Min Act: -0.0000

Data Index: 587998 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.4369. Min Act: -0.0000

Data Index: 129397 (C4 (Web Text))

Max Activating Token Index: 515

Text #17

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.4318. Min Act: -0.0000

Data Index: 1136649 (C4 (Web Text))

Max Activating Token Index: 940

Text #18

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.4036. Min Act: -0.0000

Data Index: 1197205 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.4314. Min Act: -0.0000

Data Index: 134776 (C4 (Web Text))

Max Activating Token Index: 1011