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

Dataset: The Pile

Neuron 3401 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3492. Min Range: -1.3492

Max Act: 1.3492. Min Act: -0.0000

Data Index: 1133071 (The Pile)

Max Activating Token Index: 395

Text #1

Max Range: 1.3492. Min Range: -1.3492

Max Act: 1.2672. Min Act: -0.0000

Data Index: 90323 (The Pile)

Max Activating Token Index: 395

Text #2

Max Range: 1.3492. Min Range: -1.3492

Max Act: 1.2569. Min Act: -0.0000

Data Index: 1761468 (The Pile)

Max Activating Token Index: 83

Text #3

Max Range: 1.3492. Min Range: -1.3492

Max Act: 1.1847. Min Act: -0.0000

Data Index: 1578002 (The Pile)

Max Activating Token Index: 562

Text #4

Max Range: 1.3492. Min Range: -1.3492

Max Act: 1.1692. Min Act: -0.0000

Data Index: 154172 (The Pile)

Max Activating Token Index: 273

Text #5

Max Range: 1.3492. Min Range: -1.3492

Max Act: 1.0795. Min Act: -0.0000

Data Index: 595862 (The Pile)

Max Activating Token Index: 350

Text #6

Max Range: 1.3492. Min Range: -1.3492

Max Act: 1.0397. Min Act: -0.0000

Data Index: 1703168 (The Pile)

Max Activating Token Index: 773

Text #7

Max Range: 1.3492. Min Range: -1.3492

Max Act: 1.3117. Min Act: -0.0000

Data Index: 1217366 (The Pile)

Max Activating Token Index: 546

Text #8

Max Range: 1.3492. Min Range: -1.3492

Max Act: 0.8780. Min Act: -0.0000

Data Index: 553227 (The Pile)

Max Activating Token Index: 660

Text #9

Max Range: 1.3492. Min Range: -1.3492

Max Act: 1.0572. Min Act: -0.0000

Data Index: 946017 (The Pile)

Max Activating Token Index: 189

Text #10

Max Range: 1.3492. Min Range: -1.3492

Max Act: 0.9164. Min Act: -0.0000

Data Index: 696510 (The Pile)

Max Activating Token Index: 712

Text #11

Max Range: 1.3492. Min Range: -1.3492

Max Act: 1.1548. Min Act: -0.0000

Data Index: 592009 (The Pile)

Max Activating Token Index: 287

Text #12

Max Range: 1.3492. Min Range: -1.3492

Max Act: 1.1390. Min Act: -0.0000

Data Index: 1319546 (The Pile)

Max Activating Token Index: 564

Text #13

Max Range: 1.3492. Min Range: -1.3492

Max Act: 1.0507. Min Act: -0.0000

Data Index: 1669376 (The Pile)

Max Activating Token Index: 667

Text #14

Max Range: 1.3492. Min Range: -1.3492

Max Act: 0.9013. Min Act: -0.0000

Data Index: 951600 (The Pile)

Max Activating Token Index: 680

Text #15

Max Range: 1.3492. Min Range: -1.3492

Max Act: 1.0937. Min Act: -0.0000

Data Index: 1555828 (The Pile)

Max Activating Token Index: 354

Text #16

Max Range: 1.3492. Min Range: -1.3492

Max Act: 0.9202. Min Act: -0.0000

Data Index: 934488 (The Pile)

Max Activating Token Index: 880

Text #17

Max Range: 1.3492. Min Range: -1.3492

Max Act: 1.1452. Min Act: -0.0000

Data Index: 1035223 (The Pile)

Max Activating Token Index: 358

Text #18

Max Range: 1.3492. Min Range: -1.3492

Max Act: 1.1315. Min Act: -0.0000

Data Index: 804466 (The Pile)

Max Activating Token Index: 632

Text #19

Max Range: 1.3492. Min Range: -1.3492

Max Act: 1.0302. Min Act: -0.0000

Data Index: 406098 (The Pile)

Max Activating Token Index: 443