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

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

Neuron 634 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0535. Min Act: -0.0001

Data Index: 118413 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0554. Min Act: -0.0000

Data Index: 433280 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0580. Min Act: -0.0000

Data Index: 798378 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0567. Min Act: -0.0000

Data Index: 686703 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0565. Min Act: -0.0001

Data Index: 1326932 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0532. Min Act: -0.0001

Data Index: 289368 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0538. Min Act: -0.0000

Data Index: 930096 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0522. Min Act: -0.0001

Data Index: 931153 (C4 (Web Text))

Max Activating Token Index: 197

Text #8

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0483. Min Act: -0.0001

Data Index: 559788 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0534. Min Act: -0.0001

Data Index: 145194 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0549. Min Act: -0.0000

Data Index: 175215 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0501. Min Act: -0.0001

Data Index: 617626 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0535. Min Act: -0.0001

Data Index: 1308743 (C4 (Web Text))

Max Activating Token Index: 413

Text #13

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0522. Min Act: -0.0000

Data Index: 1119417 (C4 (Web Text))

Max Activating Token Index: 417

Text #14

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0510. Min Act: -0.0001

Data Index: 727436 (C4 (Web Text))

Max Activating Token Index: 691

Text #15

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0529. Min Act: -0.0000

Data Index: 405688 (C4 (Web Text))

Max Activating Token Index: 679

Text #16

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0547. Min Act: -0.0000

Data Index: 452100 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0512. Min Act: -0.0001

Data Index: 1315617 (C4 (Web Text))

Max Activating Token Index: 198

Text #18

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0527. Min Act: -0.0001

Data Index: 499191 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 0.0580. Min Range: -0.0580

Max Act: 0.0508. Min Act: -0.0001

Data Index: 639750 (C4 (Web Text))

Max Activating Token Index: 451