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

Dataset: The Pile

Neuron 657 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: 0.5445. Min Range: -0.5445

Max Act: 0.5445. Min Act: -0.0000

Data Index: 1822833 (The Pile)

Max Activating Token Index: 363

Text #1

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4779. Min Act: -0.0000

Data Index: 1229405 (The Pile)

Max Activating Token Index: 754

Text #2

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4768. Min Act: -0.0000

Data Index: 114072 (The Pile)

Max Activating Token Index: 241

Text #3

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4392. Min Act: -0.0000

Data Index: 1915741 (The Pile)

Max Activating Token Index: 744

Text #4

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4747. Min Act: -0.0000

Data Index: 9195 (The Pile)

Max Activating Token Index: 977

Text #5

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.3270. Min Act: -0.0000

Data Index: 1169065 (The Pile)

Max Activating Token Index: 629

Text #6

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.3292. Min Act: -0.0000

Data Index: 125738 (The Pile)

Max Activating Token Index: 1015

Text #7

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.3841. Min Act: -0.0000

Data Index: 1718185 (The Pile)

Max Activating Token Index: 505

Text #8

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.3781. Min Act: -0.0000

Data Index: 1371688 (The Pile)

Max Activating Token Index: 262

Text #9

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.3708. Min Act: -0.0000

Data Index: 1984640 (The Pile)

Max Activating Token Index: 911

Text #10

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.3777. Min Act: -0.0000

Data Index: 966742 (The Pile)

Max Activating Token Index: 733

Text #11

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.3417. Min Act: -0.0000

Data Index: 1969080 (The Pile)

Max Activating Token Index: 366

Text #12

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.3019. Min Act: -0.0000

Data Index: 993828 (The Pile)

Max Activating Token Index: 849

Text #13

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.3368. Min Act: -0.0000

Data Index: 1683888 (The Pile)

Max Activating Token Index: 207

Text #14

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.3366. Min Act: -0.0000

Data Index: 1804635 (The Pile)

Max Activating Token Index: 186

Text #15

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.3638. Min Act: -0.0000

Data Index: 1283289 (The Pile)

Max Activating Token Index: 393

Text #16

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.3376. Min Act: -0.0000

Data Index: 644603 (The Pile)

Max Activating Token Index: 214

Text #17

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.3309. Min Act: -0.0000

Data Index: 1321486 (The Pile)

Max Activating Token Index: 37

Text #18

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.3171. Min Act: -0.0000

Data Index: 1319519 (The Pile)

Max Activating Token Index: 929

Text #19

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.2933. Min Act: -0.0000

Data Index: 1088830 (The Pile)

Max Activating Token Index: 215