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

Dataset: The Pile

Neuron 5008 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.3397. Min Act: -0.0000

Data Index: 1840709 (The Pile)

Max Activating Token Index: 470

Text #1

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.3652. Min Act: -0.0000

Data Index: 386386 (The Pile)

Max Activating Token Index: 812

Text #2

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.3431. Min Act: -0.0000

Data Index: 1117126 (The Pile)

Max Activating Token Index: 507

Text #3

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.3165. Min Act: -0.0000

Data Index: 1247766 (The Pile)

Max Activating Token Index: 827

Text #4

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.2879. Min Act: -0.0000

Data Index: 435160 (The Pile)

Max Activating Token Index: 289

Text #5

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.2779. Min Act: -0.0000

Data Index: 1684489 (The Pile)

Max Activating Token Index: 248

Text #6

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.2812. Min Act: -0.0000

Data Index: 965822 (The Pile)

Max Activating Token Index: 642

Text #7

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.2700. Min Act: -0.0000

Data Index: 1544690 (The Pile)

Max Activating Token Index: 207

Text #8

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.2675. Min Act: -0.0000

Data Index: 1180882 (The Pile)

Max Activating Token Index: 537

Text #9

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.2794. Min Act: -0.0000

Data Index: 109677 (The Pile)

Max Activating Token Index: 162

Text #10

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.2687. Min Act: -0.0000

Data Index: 453693 (The Pile)

Max Activating Token Index: 827

Text #11

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.2346. Min Act: -0.0000

Data Index: 1350083 (The Pile)

Max Activating Token Index: 200

Text #12

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.2569. Min Act: -0.0000

Data Index: 653896 (The Pile)

Max Activating Token Index: 490

Text #13

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.2543. Min Act: -0.0000

Data Index: 1844536 (The Pile)

Max Activating Token Index: 148

Text #14

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.3031. Min Act: -0.0000

Data Index: 1311938 (The Pile)

Max Activating Token Index: 851

Text #15

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.2504. Min Act: -0.0000

Data Index: 1790199 (The Pile)

Max Activating Token Index: 337

Text #16

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.2552. Min Act: -0.0000

Data Index: 1252348 (The Pile)

Max Activating Token Index: 694

Text #17

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.2375. Min Act: -0.0000

Data Index: 1688246 (The Pile)

Max Activating Token Index: 458

Text #18

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.2353. Min Act: -0.0000

Data Index: 1543604 (The Pile)

Max Activating Token Index: 854

Text #19

Max Range: 0.3652. Min Range: -0.3652

Max Act: 0.2346. Min Act: -0.0000

Data Index: 783337 (The Pile)

Max Activating Token Index: 46