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

Dataset: The Pile

Neuron 3686 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: 1.7777. Min Range: -1.7777

Max Act: 1.7777. Min Act: -0.0000

Data Index: 666514 (The Pile)

Max Activating Token Index: 218

Text #1

Max Range: 1.7777. Min Range: -1.7777

Max Act: 1.4220. Min Act: -0.0000

Data Index: 787287 (The Pile)

Max Activating Token Index: 591

Text #2

Max Range: 1.7777. Min Range: -1.7777

Max Act: 1.1477. Min Act: -0.0000

Data Index: 314002 (The Pile)

Max Activating Token Index: 440

Text #3

Max Range: 1.7777. Min Range: -1.7777

Max Act: 1.3605. Min Act: -0.0000

Data Index: 1063026 (The Pile)

Max Activating Token Index: 676

Text #4

Max Range: 1.7777. Min Range: -1.7777

Max Act: 1.7685. Min Act: -0.0000

Data Index: 409718 (The Pile)

Max Activating Token Index: 298

Text #5

Max Range: 1.7777. Min Range: -1.7777

Max Act: 1.6873. Min Act: -0.0000

Data Index: 227135 (The Pile)

Max Activating Token Index: 920

Text #6

Max Range: 1.7777. Min Range: -1.7777

Max Act: 1.6342. Min Act: -0.0000

Data Index: 1039597 (The Pile)

Max Activating Token Index: 547

Text #7

Max Range: 1.7777. Min Range: -1.7777

Max Act: 1.6391. Min Act: -0.0000

Data Index: 1907608 (The Pile)

Max Activating Token Index: 523

Text #8

Max Range: 1.7777. Min Range: -1.7777

Max Act: 1.2776. Min Act: -0.0000

Data Index: 1735235 (The Pile)

Max Activating Token Index: 893

Text #9

Max Range: 1.7777. Min Range: -1.7777

Max Act: 1.7486. Min Act: -0.0000

Data Index: 1851864 (The Pile)

Max Activating Token Index: 494

Text #10

Max Range: 1.7777. Min Range: -1.7777

Max Act: 1.5815. Min Act: -0.0000

Data Index: 1629288 (The Pile)

Max Activating Token Index: 304

Text #11

Max Range: 1.7777. Min Range: -1.7777

Max Act: 1.4395. Min Act: -0.0000

Data Index: 229961 (The Pile)

Max Activating Token Index: 202

Text #12

Max Range: 1.7777. Min Range: -1.7777

Max Act: 1.5592. Min Act: -0.0000

Data Index: 1110865 (The Pile)

Max Activating Token Index: 233

Text #13

Max Range: 1.7777. Min Range: -1.7777

Max Act: 1.6444. Min Act: -0.0000

Data Index: 608334 (The Pile)

Max Activating Token Index: 379

Text #14

Max Range: 1.7777. Min Range: -1.7777

Max Act: 1.6421. Min Act: -0.0000

Data Index: 832585 (The Pile)

Max Activating Token Index: 366

Text #15

Max Range: 1.7777. Min Range: -1.7777

Max Act: 1.5604. Min Act: -0.0000

Data Index: 1134621 (The Pile)

Max Activating Token Index: 723

Text #16

Max Range: 1.7777. Min Range: -1.7777

Max Act: 1.5343. Min Act: -0.0000

Data Index: 29084 (The Pile)

Max Activating Token Index: 905

Text #17

Max Range: 1.7777. Min Range: -1.7777

Max Act: 1.5365. Min Act: -0.0000

Data Index: 1356718 (The Pile)

Max Activating Token Index: 234

Text #18

Max Range: 1.7777. Min Range: -1.7777

Max Act: 1.4450. Min Act: -0.0000

Data Index: 1931362 (The Pile)

Max Activating Token Index: 911

Text #19

Max Range: 1.7777. Min Range: -1.7777

Max Act: 1.5255. Min Act: -0.0000

Data Index: 1773342 (The Pile)

Max Activating Token Index: 478