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

Dataset: The Pile

Neuron 817 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: 0.4668. Min Range: -0.4668

Max Act: 0.4668. Min Act: -0.0000

Data Index: 1507502 (The Pile)

Max Activating Token Index: 358

Text #1

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.4258. Min Act: -0.0000

Data Index: 986942 (The Pile)

Max Activating Token Index: 501

Text #2

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3895. Min Act: -0.0000

Data Index: 83513 (The Pile)

Max Activating Token Index: 482

Text #3

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3753. Min Act: -0.0000

Data Index: 1609441 (The Pile)

Max Activating Token Index: 580

Text #4

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.4005. Min Act: -0.0000

Data Index: 633717 (The Pile)

Max Activating Token Index: 217

Text #5

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3791. Min Act: -0.0000

Data Index: 1661303 (The Pile)

Max Activating Token Index: 251

Text #6

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3837. Min Act: -0.0000

Data Index: 7339 (The Pile)

Max Activating Token Index: 1021

Text #7

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3578. Min Act: -0.0000

Data Index: 1811803 (The Pile)

Max Activating Token Index: 889

Text #8

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3472. Min Act: -0.0000

Data Index: 533209 (The Pile)

Max Activating Token Index: 542

Text #9

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3482. Min Act: -0.0000

Data Index: 1233518 (The Pile)

Max Activating Token Index: 8

Text #10

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3702. Min Act: -0.0000

Data Index: 547389 (The Pile)

Max Activating Token Index: 535

Text #11

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3246. Min Act: -0.0000

Data Index: 1315337 (The Pile)

Max Activating Token Index: 734

Text #12

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3205. Min Act: -0.0000

Data Index: 688725 (The Pile)

Max Activating Token Index: 953

Text #13

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3294. Min Act: -0.0000

Data Index: 608741 (The Pile)

Max Activating Token Index: 138

Text #14

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3373. Min Act: -0.0000

Data Index: 1938675 (The Pile)

Max Activating Token Index: 69

Text #15

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3397. Min Act: -0.0000

Data Index: 661459 (The Pile)

Max Activating Token Index: 571

Text #16

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3084. Min Act: -0.0000

Data Index: 33477 (The Pile)

Max Activating Token Index: 475

Text #17

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3215. Min Act: -0.0000

Data Index: 90397 (The Pile)

Max Activating Token Index: 72

Text #18

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3296. Min Act: -0.0000

Data Index: 966203 (The Pile)

Max Activating Token Index: 582

Text #19

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3423. Min Act: -0.0000

Data Index: 1411636 (The Pile)

Max Activating Token Index: 240