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

Dataset: The Pile

Neuron 3805 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: 1.2507. Min Range: -1.2507

Max Act: 1.2064. Min Act: -0.0000

Data Index: 1917400 (The Pile)

Max Activating Token Index: 937

Text #1

Max Range: 1.2507. Min Range: -1.2507

Max Act: 1.2507. Min Act: -0.0000

Data Index: 293908 (The Pile)

Max Activating Token Index: 923

Text #2

Max Range: 1.2507. Min Range: -1.2507

Max Act: 1.0844. Min Act: -0.0000

Data Index: 1038998 (The Pile)

Max Activating Token Index: 384

Text #3

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.9725. Min Act: -0.0000

Data Index: 273856 (The Pile)

Max Activating Token Index: 33

Text #4

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.8664. Min Act: -0.0000

Data Index: 1574237 (The Pile)

Max Activating Token Index: 124

Text #5

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.9412. Min Act: -0.0000

Data Index: 545855 (The Pile)

Max Activating Token Index: 183

Text #6

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.9374. Min Act: -0.0000

Data Index: 1249971 (The Pile)

Max Activating Token Index: 594

Text #7

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.9376. Min Act: -0.0000

Data Index: 357628 (The Pile)

Max Activating Token Index: 101

Text #8

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.8764. Min Act: -0.0000

Data Index: 1231988 (The Pile)

Max Activating Token Index: 223

Text #9

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.8694. Min Act: -0.0000

Data Index: 1465218 (The Pile)

Max Activating Token Index: 31

Text #10

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.8405. Min Act: -0.0000

Data Index: 424706 (The Pile)

Max Activating Token Index: 633

Text #11

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.7783. Min Act: -0.0000

Data Index: 192273 (The Pile)

Max Activating Token Index: 878

Text #12

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.7768. Min Act: -0.0000

Data Index: 1011306 (The Pile)

Max Activating Token Index: 691

Text #13

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.8559. Min Act: -0.0000

Data Index: 1147840 (The Pile)

Max Activating Token Index: 491

Text #14

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.7934. Min Act: -0.0000

Data Index: 1567075 (The Pile)

Max Activating Token Index: 267

Text #15

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.7389. Min Act: -0.0000

Data Index: 73472 (The Pile)

Max Activating Token Index: 361

Text #16

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.7922. Min Act: -0.0000

Data Index: 675564 (The Pile)

Max Activating Token Index: 991

Text #17

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.7270. Min Act: -0.0000

Data Index: 1988600 (The Pile)

Max Activating Token Index: 719

Text #18

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.7373. Min Act: -0.0000

Data Index: 816207 (The Pile)

Max Activating Token Index: 306

Text #19

Max Range: 1.2507. Min Range: -1.2507

Max Act: 0.7666. Min Act: -0.0000

Data Index: 183457 (The Pile)

Max Activating Token Index: 614