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

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

Neuron 744 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0659. Min Act: -0.0001

Data Index: 1048929 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0602. Min Act: -0.0001

Data Index: 803095 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0506. Min Act: -0.0001

Data Index: 633264 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0472. Min Act: -0.0001

Data Index: 51753 (C4 (Web Text))

Max Activating Token Index: 498

Text #4

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0412. Min Act: -0.0001

Data Index: 812112 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0469. Min Act: -0.0001

Data Index: 397666 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0433. Min Act: -0.0001

Data Index: 695379 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0376. Min Act: -0.0001

Data Index: 1124679 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0417. Min Act: -0.0001

Data Index: 193915 (C4 (Web Text))

Max Activating Token Index: 494

Text #9

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0327. Min Act: -0.0001

Data Index: 1034984 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0370. Min Act: -0.0001

Data Index: 475384 (C4 (Web Text))

Max Activating Token Index: 575

Text #11

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0384. Min Act: -0.0001

Data Index: 14783 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0396. Min Act: -0.0001

Data Index: 980586 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0393. Min Act: -0.0001

Data Index: 291269 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0408. Min Act: -0.0001

Data Index: 187500 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0378. Min Act: -0.0001

Data Index: 441594 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0421. Min Act: -0.0001

Data Index: 771367 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0420. Min Act: -0.0001

Data Index: 733302 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0334. Min Act: -0.0001

Data Index: 867664 (C4 (Web Text))

Max Activating Token Index: 760

Text #19

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0357. Min Act: -0.0001

Data Index: 132959 (C4 (Web Text))

Max Activating Token Index: 540