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

Dataset: The Pile

Neuron 4111 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.6881. Min Act: -0.0000

Data Index: 1736024 (The Pile)

Max Activating Token Index: 574

Text #1

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.6101. Min Act: -0.0000

Data Index: 910656 (The Pile)

Max Activating Token Index: 394

Text #2

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5747. Min Act: -0.0000

Data Index: 586513 (The Pile)

Max Activating Token Index: 487

Text #3

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5397. Min Act: -0.0000

Data Index: 1241469 (The Pile)

Max Activating Token Index: 744

Text #4

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.6004. Min Act: -0.0001

Data Index: 1217154 (The Pile)

Max Activating Token Index: 786

Text #5

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5391. Min Act: -0.0000

Data Index: 1981442 (The Pile)

Max Activating Token Index: 334

Text #6

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5714. Min Act: -0.0000

Data Index: 613942 (The Pile)

Max Activating Token Index: 52

Text #7

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5540. Min Act: -0.0000

Data Index: 1029961 (The Pile)

Max Activating Token Index: 40

Text #8

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5264. Min Act: -0.0000

Data Index: 70729 (The Pile)

Max Activating Token Index: 876

Text #9

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5380. Min Act: -0.0000

Data Index: 1944871 (The Pile)

Max Activating Token Index: 485

Text #10

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5396. Min Act: -0.0000

Data Index: 752952 (The Pile)

Max Activating Token Index: 245

Text #11

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5366. Min Act: -0.0000

Data Index: 497862 (The Pile)

Max Activating Token Index: 845

Text #12

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5335. Min Act: -0.0000

Data Index: 440255 (The Pile)

Max Activating Token Index: 375

Text #13

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5726. Min Act: -0.0000

Data Index: 573598 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5480. Min Act: -0.0000

Data Index: 476005 (The Pile)

Max Activating Token Index: 7

Text #15

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.3974. Min Act: -0.0000

Data Index: 1247158 (The Pile)

Max Activating Token Index: 956

Text #16

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5267. Min Act: -0.0000

Data Index: 27197 (The Pile)

Max Activating Token Index: 423

Text #17

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5319. Min Act: -0.0000

Data Index: 338290 (The Pile)

Max Activating Token Index: 785

Text #18

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5450. Min Act: -0.0000

Data Index: 1695327 (The Pile)

Max Activating Token Index: 532

Text #19

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4933. Min Act: -0.0000

Data Index: 1644921 (The Pile)

Max Activating Token Index: 769