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

Dataset: The Pile

Neuron 3424 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: 0.4478. Min Range: -0.4478

Max Act: 0.4332. Min Act: -0.0000

Data Index: 1715629 (The Pile)

Max Activating Token Index: 441

Text #1

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3821. Min Act: -0.0000

Data Index: 79698 (The Pile)

Max Activating Token Index: 995

Text #2

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3821. Min Act: -0.0000

Data Index: 1393494 (The Pile)

Max Activating Token Index: 366

Text #3

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3790. Min Act: -0.0000

Data Index: 879709 (The Pile)

Max Activating Token Index: 716

Text #4

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3901. Min Act: -0.0000

Data Index: 849374 (The Pile)

Max Activating Token Index: 420

Text #5

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3968. Min Act: -0.0000

Data Index: 1404473 (The Pile)

Max Activating Token Index: 193

Text #6

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.4478. Min Act: -0.0000

Data Index: 1606276 (The Pile)

Max Activating Token Index: 1012

Text #7

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3764. Min Act: -0.0000

Data Index: 261678 (The Pile)

Max Activating Token Index: 579

Text #8

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.4358. Min Act: -0.0000

Data Index: 442033 (The Pile)

Max Activating Token Index: 1009

Text #9

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3448. Min Act: -0.0000

Data Index: 351125 (The Pile)

Max Activating Token Index: 346

Text #10

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3242. Min Act: -0.0000

Data Index: 1079492 (The Pile)

Max Activating Token Index: 1011

Text #11

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3327. Min Act: -0.0000

Data Index: 435018 (The Pile)

Max Activating Token Index: 939

Text #12

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3555. Min Act: -0.0000

Data Index: 1860181 (The Pile)

Max Activating Token Index: 1006

Text #13

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3659. Min Act: -0.0000

Data Index: 1296157 (The Pile)

Max Activating Token Index: 989

Text #14

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3732. Min Act: -0.0000

Data Index: 1901118 (The Pile)

Max Activating Token Index: 678

Text #15

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3577. Min Act: -0.0000

Data Index: 398242 (The Pile)

Max Activating Token Index: 215

Text #16

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3395. Min Act: -0.0000

Data Index: 635535 (The Pile)

Max Activating Token Index: 468

Text #17

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3474. Min Act: -0.0000

Data Index: 1070441 (The Pile)

Max Activating Token Index: 517

Text #18

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3697. Min Act: -0.0000

Data Index: 1936240 (The Pile)

Max Activating Token Index: 590

Text #19

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3246. Min Act: -0.0000

Data Index: 22235 (The Pile)

Max Activating Token Index: 955