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

Dataset: The Pile

Neuron 3182 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.4838. Min Act: -0.0000

Data Index: 1797588 (The Pile)

Max Activating Token Index: 257

Text #1

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.4348. Min Act: -0.0000

Data Index: 1973847 (The Pile)

Max Activating Token Index: 997

Text #2

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.3618. Min Act: -0.0000

Data Index: 545028 (The Pile)

Max Activating Token Index: 913

Text #3

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.4618. Min Act: -0.0000

Data Index: 706727 (The Pile)

Max Activating Token Index: 539

Text #4

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.3873. Min Act: -0.0000

Data Index: 484499 (The Pile)

Max Activating Token Index: 1006

Text #5

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.4532. Min Act: -0.0000

Data Index: 170056 (The Pile)

Max Activating Token Index: 269

Text #6

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.4011. Min Act: -0.0000

Data Index: 1839431 (The Pile)

Max Activating Token Index: 671

Text #7

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.3291. Min Act: -0.0000

Data Index: 1231335 (The Pile)

Max Activating Token Index: 532

Text #8

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.3549. Min Act: -0.0000

Data Index: 787852 (The Pile)

Max Activating Token Index: 205

Text #9

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.3260. Min Act: -0.0000

Data Index: 768218 (The Pile)

Max Activating Token Index: 566

Text #10

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.2578. Min Act: -0.0000

Data Index: 1876475 (The Pile)

Max Activating Token Index: 416

Text #11

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.2960. Min Act: -0.0000

Data Index: 1363570 (The Pile)

Max Activating Token Index: 596

Text #12

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.3159. Min Act: -0.0000

Data Index: 1068329 (The Pile)

Max Activating Token Index: 594

Text #13

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.3021. Min Act: -0.0000

Data Index: 335207 (The Pile)

Max Activating Token Index: 89

Text #14

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.2808. Min Act: -0.0000

Data Index: 570988 (The Pile)

Max Activating Token Index: 986

Text #15

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.2773. Min Act: -0.0000

Data Index: 1033095 (The Pile)

Max Activating Token Index: 708

Text #16

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.2503. Min Act: -0.0000

Data Index: 1072189 (The Pile)

Max Activating Token Index: 271

Text #17

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.2754. Min Act: -0.0000

Data Index: 1809231 (The Pile)

Max Activating Token Index: 325

Text #18

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.2134. Min Act: -0.0000

Data Index: 1030448 (The Pile)

Max Activating Token Index: 121

Text #19

Max Range: 1.4838. Min Range: -1.4838

Max Act: 1.2027. Min Act: -0.0000

Data Index: 75566 (The Pile)

Max Activating Token Index: 637