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

Dataset: The Pile

Neuron 4160 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4967. Min Range: -0.4967

Max Act: 0.4601. Min Act: -0.0000

Data Index: 129459 (The Pile)

Max Activating Token Index: 649

Text #1

Max Range: 0.4967. Min Range: -0.4967

Max Act: 0.4967. Min Act: -0.0000

Data Index: 1443708 (The Pile)

Max Activating Token Index: 145

Text #2

Max Range: 0.4967. Min Range: -0.4967

Max Act: 0.3545. Min Act: -0.0000

Data Index: 203101 (The Pile)

Max Activating Token Index: 468

Text #3

Max Range: 0.4967. Min Range: -0.4967

Max Act: 0.2648. Min Act: -0.0000

Data Index: 224421 (The Pile)

Max Activating Token Index: 861

Text #4

Max Range: 0.4967. Min Range: -0.4967

Max Act: 0.3097. Min Act: -0.0000

Data Index: 641172 (The Pile)

Max Activating Token Index: 41

Text #5

Max Range: 0.4967. Min Range: -0.4967

Max Act: 0.2749. Min Act: -0.0000

Data Index: 1890637 (The Pile)

Max Activating Token Index: 11

Text #6

Max Range: 0.4967. Min Range: -0.4967

Max Act: 0.2659. Min Act: -0.0000

Data Index: 635570 (The Pile)

Max Activating Token Index: 384

Text #7

Max Range: 0.4967. Min Range: -0.4967

Max Act: 0.2592. Min Act: -0.0000

Data Index: 295736 (The Pile)

Max Activating Token Index: 128

Text #8

Max Range: 0.4967. Min Range: -0.4967

Max Act: 0.2614. Min Act: -0.0000

Data Index: 1752 (The Pile)

Max Activating Token Index: 436

Text #9

Max Range: 0.4967. Min Range: -0.4967

Max Act: 0.2602. Min Act: -0.0000

Data Index: 1871730 (The Pile)

Max Activating Token Index: 385

Text #10

Max Range: 0.4967. Min Range: -0.4967

Max Act: 0.2623. Min Act: -0.0000

Data Index: 559845 (The Pile)

Max Activating Token Index: 687

Text #11

Max Range: 0.4967. Min Range: -0.4967

Max Act: 0.2309. Min Act: -0.0000

Data Index: 152441 (The Pile)

Max Activating Token Index: 425

Text #12

Max Range: 0.4967. Min Range: -0.4967

Max Act: 0.2391. Min Act: -0.0000

Data Index: 626185 (The Pile)

Max Activating Token Index: 124

Text #13

Max Range: 0.4967. Min Range: -0.4967

Max Act: 0.2356. Min Act: -0.0000

Data Index: 1057564 (The Pile)

Max Activating Token Index: 203

Text #14

Max Range: 0.4967. Min Range: -0.4967

Max Act: 0.2200. Min Act: -0.0000

Data Index: 512338 (The Pile)

Max Activating Token Index: 430

Text #15

Max Range: 0.4967. Min Range: -0.4967

Max Act: 0.2496. Min Act: -0.0000

Data Index: 882803 (The Pile)

Max Activating Token Index: 327

Text #16

Max Range: 0.4967. Min Range: -0.4967

Max Act: 0.2353. Min Act: -0.0000

Data Index: 459895 (The Pile)

Max Activating Token Index: 724

Text #17

Max Range: 0.4967. Min Range: -0.4967

Max Act: 0.2159. Min Act: -0.0000

Data Index: 859961 (The Pile)

Max Activating Token Index: 743

Text #18

Max Range: 0.4967. Min Range: -0.4967

Max Act: 0.1962. Min Act: -0.0000

Data Index: 1303841 (The Pile)

Max Activating Token Index: 528

Text #19

Max Range: 0.4967. Min Range: -0.4967

Max Act: 0.2204. Min Act: -0.0000

Data Index: 1630322 (The Pile)

Max Activating Token Index: 195