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

Dataset: The Pile

Neuron 1568 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.6374. Min Act: -0.0000

Data Index: 1311516 (The Pile)

Max Activating Token Index: 107

Text #1

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.5239. Min Act: -0.0000

Data Index: 106095 (The Pile)

Max Activating Token Index: 797

Text #2

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.5912. Min Act: -0.0000

Data Index: 1851617 (The Pile)

Max Activating Token Index: 122

Text #3

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.6806. Min Act: -0.0000

Data Index: 737926 (The Pile)

Max Activating Token Index: 444

Text #4

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.5544. Min Act: -0.0000

Data Index: 963903 (The Pile)

Max Activating Token Index: 747

Text #5

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.5318. Min Act: -0.0000

Data Index: 1875704 (The Pile)

Max Activating Token Index: 410

Text #6

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.4784. Min Act: -0.0000

Data Index: 452490 (The Pile)

Max Activating Token Index: 604

Text #7

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.4360. Min Act: -0.0000

Data Index: 77450 (The Pile)

Max Activating Token Index: 393

Text #8

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.4837. Min Act: -0.0000

Data Index: 173421 (The Pile)

Max Activating Token Index: 322

Text #9

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.5638. Min Act: -0.0000

Data Index: 1019825 (The Pile)

Max Activating Token Index: 513

Text #10

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.5118. Min Act: -0.0000

Data Index: 1337264 (The Pile)

Max Activating Token Index: 368

Text #11

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.3313. Min Act: -0.0000

Data Index: 1047909 (The Pile)

Max Activating Token Index: 399

Text #12

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.2472. Min Act: -0.0000

Data Index: 1079219 (The Pile)

Max Activating Token Index: 188

Text #13

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.3228. Min Act: -0.0000

Data Index: 1630470 (The Pile)

Max Activating Token Index: 999

Text #14

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.3113. Min Act: -0.0000

Data Index: 860067 (The Pile)

Max Activating Token Index: 29

Text #15

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.4600. Min Act: -0.0000

Data Index: 235203 (The Pile)

Max Activating Token Index: 524

Text #16

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.4028. Min Act: -0.0000

Data Index: 9084 (The Pile)

Max Activating Token Index: 404

Text #17

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.5296. Min Act: -0.0000

Data Index: 1425556 (The Pile)

Max Activating Token Index: 482

Text #18

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.3195. Min Act: -0.0000

Data Index: 1590636 (The Pile)

Max Activating Token Index: 470

Text #19

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.2939. Min Act: -0.0000

Data Index: 1437969 (The Pile)

Max Activating Token Index: 240