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

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

Neuron 4529 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0723. Min Act: -0.0002

Data Index: 454547 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0677. Min Act: -0.0002

Data Index: 679753 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0589. Min Act: -0.0002

Data Index: 437727 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0626. Min Act: -0.0002

Data Index: 241761 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0625. Min Act: -0.0002

Data Index: 442602 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0627. Min Act: -0.0002

Data Index: 708903 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0558. Min Act: -0.0002

Data Index: 1210505 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0495. Min Act: -0.0002

Data Index: 1305027 (C4 (Web Text))

Max Activating Token Index: 323

Text #8

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0627. Min Act: -0.0002

Data Index: 387336 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0561. Min Act: -0.0002

Data Index: 567148 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0458. Min Act: -0.0002

Data Index: 334711 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0568. Min Act: -0.0002

Data Index: 1425245 (Python Code)

Max Activating Token Index: 10

Text #12

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0630. Min Act: -0.0002

Data Index: 110388 (C4 (Web Text))

Max Activating Token Index: 259

Text #13

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0577. Min Act: -0.0002

Data Index: 1322717 (C4 (Web Text))

Max Activating Token Index: 123

Text #14

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0510. Min Act: -0.0002

Data Index: 664175 (C4 (Web Text))

Max Activating Token Index: 203

Text #15

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0531. Min Act: -0.0002

Data Index: 1452936 (Python Code)

Max Activating Token Index: 245

Text #16

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0554. Min Act: -0.0002

Data Index: 770327 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0483. Min Act: -0.0002

Data Index: 714810 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0468. Min Act: -0.0002

Data Index: 311734 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0589. Min Act: -0.0002

Data Index: 876535 (C4 (Web Text))

Max Activating Token Index: 195