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

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

Neuron 4708 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5703. Min Range: -0.5703

Max Act: 0.5703. Min Act: -0.0000

Data Index: 905872 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 0.5703. Min Range: -0.5703

Max Act: 0.4963. Min Act: -0.0000

Data Index: 1029829 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 0.5703. Min Range: -0.5703

Max Act: 0.4826. Min Act: -0.0000

Data Index: 1215820 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 0.5703. Min Range: -0.5703

Max Act: 0.4511. Min Act: -0.0000

Data Index: 748723 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 0.5703. Min Range: -0.5703

Max Act: 0.4401. Min Act: -0.0000

Data Index: 513338 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 0.5703. Min Range: -0.5703

Max Act: 0.4651. Min Act: -0.0000

Data Index: 1304717 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 0.5703. Min Range: -0.5703

Max Act: 0.4251. Min Act: -0.0000

Data Index: 108714 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 0.5703. Min Range: -0.5703

Max Act: 0.3626. Min Act: -0.0000

Data Index: 605436 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 0.5703. Min Range: -0.5703

Max Act: 0.4073. Min Act: -0.0000

Data Index: 788385 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 0.5703. Min Range: -0.5703

Max Act: 0.4084. Min Act: -0.0000

Data Index: 1123736 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 0.5703. Min Range: -0.5703

Max Act: 0.3489. Min Act: -0.0000

Data Index: 1282100 (C4 (Web Text))

Max Activating Token Index: 844

Text #11

Max Range: 0.5703. Min Range: -0.5703

Max Act: 0.3615. Min Act: -0.0000

Data Index: 1351790 (C4 (Web Text))

Max Activating Token Index: 629

Text #12

Max Range: 0.5703. Min Range: -0.5703

Max Act: 0.3622. Min Act: -0.0000

Data Index: 1238578 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 0.5703. Min Range: -0.5703

Max Act: 0.3555. Min Act: -0.0000

Data Index: 365084 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 0.5703. Min Range: -0.5703

Max Act: 0.3483. Min Act: -0.0000

Data Index: 1412752 (Python Code)

Max Activating Token Index: 183

Text #15

Max Range: 0.5703. Min Range: -0.5703

Max Act: 0.3264. Min Act: -0.0000

Data Index: 999399 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 0.5703. Min Range: -0.5703

Max Act: 0.3489. Min Act: -0.0000

Data Index: 356835 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 0.5703. Min Range: -0.5703

Max Act: 0.3559. Min Act: -0.0000

Data Index: 176641 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 0.5703. Min Range: -0.5703

Max Act: 0.3897. Min Act: -0.0000

Data Index: 1079527 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 0.5703. Min Range: -0.5703

Max Act: 0.3457. Min Act: -0.0000

Data Index: 465294 (C4 (Web Text))

Max Activating Token Index: 940