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

Dataset: The Pile

Neuron 1958 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: 5.6301. Min Range: -5.6301

Max Act: 5.6301. Min Act: -0.0000

Data Index: 78768 (The Pile)

Max Activating Token Index: 752

Text #1

Max Range: 5.6301. Min Range: -5.6301

Max Act: 5.0397. Min Act: -0.0000

Data Index: 870996 (The Pile)

Max Activating Token Index: 781

Text #2

Max Range: 5.6301. Min Range: -5.6301

Max Act: 4.1845. Min Act: -0.0000

Data Index: 912948 (The Pile)

Max Activating Token Index: 82

Text #3

Max Range: 5.6301. Min Range: -5.6301

Max Act: 4.8864. Min Act: -0.0000

Data Index: 1729722 (The Pile)

Max Activating Token Index: 293

Text #4

Max Range: 5.6301. Min Range: -5.6301

Max Act: 4.4363. Min Act: -0.0000

Data Index: 1835141 (The Pile)

Max Activating Token Index: 175

Text #5

Max Range: 5.6301. Min Range: -5.6301

Max Act: 4.4186. Min Act: -0.0000

Data Index: 1821690 (The Pile)

Max Activating Token Index: 93

Text #6

Max Range: 5.6301. Min Range: -5.6301

Max Act: 4.0801. Min Act: -0.0000

Data Index: 903392 (The Pile)

Max Activating Token Index: 507

Text #7

Max Range: 5.6301. Min Range: -5.6301

Max Act: 4.0845. Min Act: -0.0000

Data Index: 695275 (The Pile)

Max Activating Token Index: 69

Text #8

Max Range: 5.6301. Min Range: -5.6301

Max Act: 4.3834. Min Act: -0.0000

Data Index: 1611409 (The Pile)

Max Activating Token Index: 71

Text #9

Max Range: 5.6301. Min Range: -5.6301

Max Act: 3.9242. Min Act: -0.0000

Data Index: 614281 (The Pile)

Max Activating Token Index: 539

Text #10

Max Range: 5.6301. Min Range: -5.6301

Max Act: 3.5931. Min Act: -0.0000

Data Index: 385427 (The Pile)

Max Activating Token Index: 636

Text #11

Max Range: 5.6301. Min Range: -5.6301

Max Act: 3.9046. Min Act: -0.0000

Data Index: 1967274 (The Pile)

Max Activating Token Index: 525

Text #12

Max Range: 5.6301. Min Range: -5.6301

Max Act: 4.2212. Min Act: -0.0000

Data Index: 1244560 (The Pile)

Max Activating Token Index: 844

Text #13

Max Range: 5.6301. Min Range: -5.6301

Max Act: 3.9787. Min Act: -0.0000

Data Index: 1459968 (The Pile)

Max Activating Token Index: 74

Text #14

Max Range: 5.6301. Min Range: -5.6301

Max Act: 4.3145. Min Act: -0.0000

Data Index: 1068606 (The Pile)

Max Activating Token Index: 504

Text #15

Max Range: 5.6301. Min Range: -5.6301

Max Act: 4.0728. Min Act: -0.0000

Data Index: 106638 (The Pile)

Max Activating Token Index: 874

Text #16

Max Range: 5.6301. Min Range: -5.6301

Max Act: 3.8745. Min Act: -0.0000

Data Index: 1730840 (The Pile)

Max Activating Token Index: 494

Text #17

Max Range: 5.6301. Min Range: -5.6301

Max Act: 3.8915. Min Act: -0.0000

Data Index: 350554 (The Pile)

Max Activating Token Index: 755

Text #18

Max Range: 5.6301. Min Range: -5.6301

Max Act: 3.6992. Min Act: -0.0000

Data Index: 642804 (The Pile)

Max Activating Token Index: 724

Text #19

Max Range: 5.6301. Min Range: -5.6301

Max Act: 3.6517. Min Act: -0.0000

Data Index: 495699 (The Pile)

Max Activating Token Index: 692