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

Dataset: The Pile

Neuron 339 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: 1.8898. Min Range: -1.8898

Max Act: 1.4172. Min Act: -0.0000

Data Index: 328127 (The Pile)

Max Activating Token Index: 389

Text #1

Max Range: 1.8898. Min Range: -1.8898

Max Act: 1.8898. Min Act: -0.0000

Data Index: 1934995 (The Pile)

Max Activating Token Index: 428

Text #2

Max Range: 1.8898. Min Range: -1.8898

Max Act: 1.6812. Min Act: -0.0000

Data Index: 955858 (The Pile)

Max Activating Token Index: 186

Text #3

Max Range: 1.8898. Min Range: -1.8898

Max Act: 1.3957. Min Act: -0.0000

Data Index: 1348212 (The Pile)

Max Activating Token Index: 617

Text #4

Max Range: 1.8898. Min Range: -1.8898

Max Act: 1.5978. Min Act: -0.0000

Data Index: 1683645 (The Pile)

Max Activating Token Index: 285

Text #5

Max Range: 1.8898. Min Range: -1.8898

Max Act: 1.5587. Min Act: -0.0000

Data Index: 387553 (The Pile)

Max Activating Token Index: 574

Text #6

Max Range: 1.8898. Min Range: -1.8898

Max Act: 1.2542. Min Act: -0.0000

Data Index: 1325298 (The Pile)

Max Activating Token Index: 942

Text #7

Max Range: 1.8898. Min Range: -1.8898

Max Act: 1.2101. Min Act: -0.0000

Data Index: 329741 (The Pile)

Max Activating Token Index: 563

Text #8

Max Range: 1.8898. Min Range: -1.8898

Max Act: 1.4347. Min Act: -0.0000

Data Index: 301677 (The Pile)

Max Activating Token Index: 877

Text #9

Max Range: 1.8898. Min Range: -1.8898

Max Act: 1.3318. Min Act: -0.0000

Data Index: 705601 (The Pile)

Max Activating Token Index: 405

Text #10

Max Range: 1.8898. Min Range: -1.8898

Max Act: 1.1319. Min Act: -0.0000

Data Index: 274044 (The Pile)

Max Activating Token Index: 314

Text #11

Max Range: 1.8898. Min Range: -1.8898

Max Act: 1.1703. Min Act: -0.0000

Data Index: 1642855 (The Pile)

Max Activating Token Index: 655

Text #12

Max Range: 1.8898. Min Range: -1.8898

Max Act: 1.0756. Min Act: -0.0000

Data Index: 236439 (The Pile)

Max Activating Token Index: 901

Text #13

Max Range: 1.8898. Min Range: -1.8898

Max Act: 1.0342. Min Act: -0.0000

Data Index: 1842552 (The Pile)

Max Activating Token Index: 894

Text #14

Max Range: 1.8898. Min Range: -1.8898

Max Act: 1.1847. Min Act: -0.0000

Data Index: 1592580 (The Pile)

Max Activating Token Index: 503

Text #15

Max Range: 1.8898. Min Range: -1.8898

Max Act: 1.0807. Min Act: -0.0000

Data Index: 980320 (The Pile)

Max Activating Token Index: 721

Text #16

Max Range: 1.8898. Min Range: -1.8898

Max Act: 1.1704. Min Act: -0.0000

Data Index: 1779968 (The Pile)

Max Activating Token Index: 332

Text #17

Max Range: 1.8898. Min Range: -1.8898

Max Act: 1.1661. Min Act: -0.0000

Data Index: 454371 (The Pile)

Max Activating Token Index: 229

Text #18

Max Range: 1.8898. Min Range: -1.8898

Max Act: 1.0161. Min Act: -0.0000

Data Index: 1646751 (The Pile)

Max Activating Token Index: 84

Text #19

Max Range: 1.8898. Min Range: -1.8898

Max Act: 1.0288. Min Act: -0.0000

Data Index: 292248 (The Pile)

Max Activating Token Index: 428