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

Dataset: The Pile

Neuron 4653 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: 3.1992. Min Range: -3.1992

Max Act: 3.1992. Min Act: -0.0000

Data Index: 1815087 (The Pile)

Max Activating Token Index: 607

Text #1

Max Range: 3.1992. Min Range: -3.1992

Max Act: 2.2724. Min Act: -0.0000

Data Index: 1893178 (The Pile)

Max Activating Token Index: 900

Text #2

Max Range: 3.1992. Min Range: -3.1992

Max Act: 2.3102. Min Act: -0.0000

Data Index: 1634931 (The Pile)

Max Activating Token Index: 235

Text #3

Max Range: 3.1992. Min Range: -3.1992

Max Act: 2.5547. Min Act: -0.0000

Data Index: 888627 (The Pile)

Max Activating Token Index: 458

Text #4

Max Range: 3.1992. Min Range: -3.1992

Max Act: 2.3825. Min Act: -0.0000

Data Index: 123940 (The Pile)

Max Activating Token Index: 704

Text #5

Max Range: 3.1992. Min Range: -3.1992

Max Act: 2.3842. Min Act: -0.0000

Data Index: 439733 (The Pile)

Max Activating Token Index: 381

Text #6

Max Range: 3.1992. Min Range: -3.1992

Max Act: 2.2563. Min Act: -0.0000

Data Index: 559957 (The Pile)

Max Activating Token Index: 82

Text #7

Max Range: 3.1992. Min Range: -3.1992

Max Act: 2.3568. Min Act: -0.0000

Data Index: 486626 (The Pile)

Max Activating Token Index: 192

Text #8

Max Range: 3.1992. Min Range: -3.1992

Max Act: 2.3105. Min Act: -0.0000

Data Index: 1197089 (The Pile)

Max Activating Token Index: 313

Text #9

Max Range: 3.1992. Min Range: -3.1992

Max Act: 2.2913. Min Act: -0.0000

Data Index: 1764046 (The Pile)

Max Activating Token Index: 269

Text #10

Max Range: 3.1992. Min Range: -3.1992

Max Act: 2.1858. Min Act: -0.0000

Data Index: 525038 (The Pile)

Max Activating Token Index: 999

Text #11

Max Range: 3.1992. Min Range: -3.1992

Max Act: 2.4509. Min Act: -0.0000

Data Index: 1375415 (The Pile)

Max Activating Token Index: 218

Text #12

Max Range: 3.1992. Min Range: -3.1992

Max Act: 1.8807. Min Act: -0.0000

Data Index: 287444 (The Pile)

Max Activating Token Index: 197

Text #13

Max Range: 3.1992. Min Range: -3.1992

Max Act: 1.9779. Min Act: -0.0000

Data Index: 1877284 (The Pile)

Max Activating Token Index: 290

Text #14

Max Range: 3.1992. Min Range: -3.1992

Max Act: 1.9464. Min Act: -0.0000

Data Index: 604779 (The Pile)

Max Activating Token Index: 365

Text #15

Max Range: 3.1992. Min Range: -3.1992

Max Act: 1.9445. Min Act: -0.0000

Data Index: 262422 (The Pile)

Max Activating Token Index: 342

Text #16

Max Range: 3.1992. Min Range: -3.1992

Max Act: 2.0299. Min Act: -0.0000

Data Index: 1574511 (The Pile)

Max Activating Token Index: 560

Text #17

Max Range: 3.1992. Min Range: -3.1992

Max Act: 1.9384. Min Act: -0.0000

Data Index: 335066 (The Pile)

Max Activating Token Index: 468

Text #18

Max Range: 3.1992. Min Range: -3.1992

Max Act: 1.9185. Min Act: -0.0000

Data Index: 1391996 (The Pile)

Max Activating Token Index: 956

Text #19

Max Range: 3.1992. Min Range: -3.1992

Max Act: 2.1006. Min Act: -0.0000

Data Index: 797620 (The Pile)

Max Activating Token Index: 202