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

Dataset: The Pile

Neuron 3717 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.6459. Min Act: -0.0000

Data Index: 1021446 (The Pile)

Max Activating Token Index: 214

Text #1

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.8389. Min Act: -0.0000

Data Index: 1365658 (The Pile)

Max Activating Token Index: 431

Text #2

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.5385. Min Act: -0.0000

Data Index: 339978 (The Pile)

Max Activating Token Index: 316

Text #3

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.6272. Min Act: -0.0000

Data Index: 315331 (The Pile)

Max Activating Token Index: 284

Text #4

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.5915. Min Act: -0.0000

Data Index: 1647549 (The Pile)

Max Activating Token Index: 50

Text #5

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.5660. Min Act: -0.0000

Data Index: 370319 (The Pile)

Max Activating Token Index: 648

Text #6

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.2727. Min Act: -0.0000

Data Index: 726163 (The Pile)

Max Activating Token Index: 823

Text #7

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.4966. Min Act: -0.0000

Data Index: 1407416 (The Pile)

Max Activating Token Index: 174

Text #8

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.4212. Min Act: -0.0000

Data Index: 1284259 (The Pile)

Max Activating Token Index: 548

Text #9

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.4864. Min Act: -0.0000

Data Index: 1274063 (The Pile)

Max Activating Token Index: 394

Text #10

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.3939. Min Act: -0.0000

Data Index: 451618 (The Pile)

Max Activating Token Index: 335

Text #11

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.3957. Min Act: -0.0000

Data Index: 570706 (The Pile)

Max Activating Token Index: 724

Text #12

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.4579. Min Act: -0.0000

Data Index: 123395 (The Pile)

Max Activating Token Index: 355

Text #13

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.3894. Min Act: -0.0000

Data Index: 301388 (The Pile)

Max Activating Token Index: 541

Text #14

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.3353. Min Act: -0.0000

Data Index: 1522168 (The Pile)

Max Activating Token Index: 977

Text #15

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.3948. Min Act: -0.0000

Data Index: 1466950 (The Pile)

Max Activating Token Index: 606

Text #16

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.2315. Min Act: -0.0000

Data Index: 582034 (The Pile)

Max Activating Token Index: 182

Text #17

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.3156. Min Act: -0.0000

Data Index: 1976895 (The Pile)

Max Activating Token Index: 396

Text #18

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.3075. Min Act: -0.0000

Data Index: 1548163 (The Pile)

Max Activating Token Index: 816

Text #19

Max Range: 1.8389. Min Range: -1.8389

Max Act: 1.2872. Min Act: -0.0000

Data Index: 1673017 (The Pile)

Max Activating Token Index: 103