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

Dataset: The Pile

Neuron 3525 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.6948. Min Act: -0.0000

Data Index: 1515139 (The Pile)

Max Activating Token Index: 1017

Text #1

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.6405. Min Act: -0.0000

Data Index: 1022837 (The Pile)

Max Activating Token Index: 284

Text #2

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.4536. Min Act: -0.0000

Data Index: 1796541 (The Pile)

Max Activating Token Index: 216

Text #3

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5644. Min Act: -0.0000

Data Index: 909611 (The Pile)

Max Activating Token Index: 527

Text #4

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5389. Min Act: -0.0000

Data Index: 1718309 (The Pile)

Max Activating Token Index: 608

Text #5

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5457. Min Act: -0.0000

Data Index: 213146 (The Pile)

Max Activating Token Index: 352

Text #6

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5358. Min Act: -0.0000

Data Index: 160106 (The Pile)

Max Activating Token Index: 121

Text #7

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5372. Min Act: -0.0000

Data Index: 1915577 (The Pile)

Max Activating Token Index: 534

Text #8

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5519. Min Act: -0.0000

Data Index: 117824 (The Pile)

Max Activating Token Index: 385

Text #9

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5150. Min Act: -0.0000

Data Index: 1151805 (The Pile)

Max Activating Token Index: 238

Text #10

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5273. Min Act: -0.0000

Data Index: 1866086 (The Pile)

Max Activating Token Index: 767

Text #11

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5194. Min Act: -0.0000

Data Index: 1688081 (The Pile)

Max Activating Token Index: 547

Text #12

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5025. Min Act: -0.0000

Data Index: 1291533 (The Pile)

Max Activating Token Index: 935

Text #13

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5373. Min Act: -0.0000

Data Index: 1944557 (The Pile)

Max Activating Token Index: 785

Text #14

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.4939. Min Act: -0.0000

Data Index: 175259 (The Pile)

Max Activating Token Index: 602

Text #15

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5045. Min Act: -0.0000

Data Index: 613522 (The Pile)

Max Activating Token Index: 759

Text #16

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5134. Min Act: -0.0000

Data Index: 637840 (The Pile)

Max Activating Token Index: 874

Text #17

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.4808. Min Act: -0.0000

Data Index: 509167 (The Pile)

Max Activating Token Index: 691

Text #18

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5089. Min Act: -0.0000

Data Index: 1781533 (The Pile)

Max Activating Token Index: 731

Text #19

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5109. Min Act: -0.0000

Data Index: 862105 (The Pile)

Max Activating Token Index: 69