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

Dataset: The Pile

Neuron 1815 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.9350. Min Act: -0.0000

Data Index: 969581 (The Pile)

Max Activating Token Index: 220

Text #1

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.9117. Min Act: -0.0000

Data Index: 1021294 (The Pile)

Max Activating Token Index: 149

Text #2

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.9232. Min Act: -0.0000

Data Index: 151431 (The Pile)

Max Activating Token Index: 40

Text #3

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.8498. Min Act: -0.0000

Data Index: 213445 (The Pile)

Max Activating Token Index: 971

Text #4

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.9605. Min Act: -0.0000

Data Index: 369635 (The Pile)

Max Activating Token Index: 586

Text #5

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.8394. Min Act: -0.0000

Data Index: 1787970 (The Pile)

Max Activating Token Index: 694

Text #6

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.7007. Min Act: -0.0000

Data Index: 823962 (The Pile)

Max Activating Token Index: 344

Text #7

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.8593. Min Act: -0.0000

Data Index: 1576254 (The Pile)

Max Activating Token Index: 359

Text #8

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.7864. Min Act: -0.0000

Data Index: 1649051 (The Pile)

Max Activating Token Index: 523

Text #9

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.7814. Min Act: -0.0000

Data Index: 561974 (The Pile)

Max Activating Token Index: 404

Text #10

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.8410. Min Act: -0.0000

Data Index: 1878414 (The Pile)

Max Activating Token Index: 171

Text #11

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.8126. Min Act: -0.0000

Data Index: 1385204 (The Pile)

Max Activating Token Index: 1002

Text #12

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.7542. Min Act: -0.0000

Data Index: 1185010 (The Pile)

Max Activating Token Index: 44

Text #13

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.7947. Min Act: -0.0000

Data Index: 1748694 (The Pile)

Max Activating Token Index: 350

Text #14

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.8349. Min Act: -0.0000

Data Index: 1163217 (The Pile)

Max Activating Token Index: 792

Text #15

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.8237. Min Act: -0.0000

Data Index: 1752515 (The Pile)

Max Activating Token Index: 756

Text #16

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.7789. Min Act: -0.0000

Data Index: 1008217 (The Pile)

Max Activating Token Index: 398

Text #17

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.7359. Min Act: -0.0000

Data Index: 1024519 (The Pile)

Max Activating Token Index: 717

Text #18

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.8438. Min Act: -0.0000

Data Index: 833592 (The Pile)

Max Activating Token Index: 872

Text #19

Max Range: 0.9605. Min Range: -0.9605

Max Act: 0.7835. Min Act: -0.0000

Data Index: 1956976 (The Pile)

Max Activating Token Index: 742