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

Dataset: The Pile

Neuron 3347 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: 0.3906. Min Range: -0.3906

Max Act: 0.3887. Min Act: -0.0000

Data Index: 1727437 (The Pile)

Max Activating Token Index: 552

Text #1

Max Range: 0.3906. Min Range: -0.3906

Max Act: 0.3224. Min Act: -0.0000

Data Index: 708201 (The Pile)

Max Activating Token Index: 542

Text #2

Max Range: 0.3906. Min Range: -0.3906

Max Act: 0.3906. Min Act: -0.0000

Data Index: 1366962 (The Pile)

Max Activating Token Index: 491

Text #3

Max Range: 0.3906. Min Range: -0.3906

Max Act: 0.3432. Min Act: -0.0000

Data Index: 1069505 (The Pile)

Max Activating Token Index: 430

Text #4

Max Range: 0.3906. Min Range: -0.3906

Max Act: 0.3391. Min Act: -0.0000

Data Index: 127394 (The Pile)

Max Activating Token Index: 491

Text #5

Max Range: 0.3906. Min Range: -0.3906

Max Act: 0.2960. Min Act: -0.0000

Data Index: 1545529 (The Pile)

Max Activating Token Index: 337

Text #6

Max Range: 0.3906. Min Range: -0.3906

Max Act: 0.3371. Min Act: -0.0000

Data Index: 1008621 (The Pile)

Max Activating Token Index: 332

Text #7

Max Range: 0.3906. Min Range: -0.3906

Max Act: 0.2960. Min Act: -0.0000

Data Index: 1312592 (The Pile)

Max Activating Token Index: 780

Text #8

Max Range: 0.3906. Min Range: -0.3906

Max Act: 0.3176. Min Act: -0.0000

Data Index: 163252 (The Pile)

Max Activating Token Index: 335

Text #9

Max Range: 0.3906. Min Range: -0.3906

Max Act: 0.3164. Min Act: -0.0000

Data Index: 1812979 (The Pile)

Max Activating Token Index: 482

Text #10

Max Range: 0.3906. Min Range: -0.3906

Max Act: 0.3047. Min Act: -0.0000

Data Index: 1988501 (The Pile)

Max Activating Token Index: 488

Text #11

Max Range: 0.3906. Min Range: -0.3906

Max Act: 0.2519. Min Act: -0.0000

Data Index: 117555 (The Pile)

Max Activating Token Index: 509

Text #12

Max Range: 0.3906. Min Range: -0.3906

Max Act: 0.2771. Min Act: -0.0000

Data Index: 429655 (The Pile)

Max Activating Token Index: 267

Text #13

Max Range: 0.3906. Min Range: -0.3906

Max Act: 0.2705. Min Act: -0.0000

Data Index: 1515645 (The Pile)

Max Activating Token Index: 573

Text #14

Max Range: 0.3906. Min Range: -0.3906

Max Act: 0.2616. Min Act: -0.0000

Data Index: 1887042 (The Pile)

Max Activating Token Index: 763

Text #15

Max Range: 0.3906. Min Range: -0.3906

Max Act: 0.2453. Min Act: -0.0000

Data Index: 81239 (The Pile)

Max Activating Token Index: 117

Text #16

Max Range: 0.3906. Min Range: -0.3906

Max Act: 0.2611. Min Act: -0.0000

Data Index: 1621309 (The Pile)

Max Activating Token Index: 250

Text #17

Max Range: 0.3906. Min Range: -0.3906

Max Act: 0.3313. Min Act: -0.0000

Data Index: 1768768 (The Pile)

Max Activating Token Index: 851

Text #18

Max Range: 0.3906. Min Range: -0.3906

Max Act: 0.2302. Min Act: -0.0000

Data Index: 1270981 (The Pile)

Max Activating Token Index: 395

Text #19

Max Range: 0.3906. Min Range: -0.3906

Max Act: 0.2333. Min Act: -0.0000

Data Index: 1295937 (The Pile)

Max Activating Token Index: 472