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

Dataset: The Pile

Neuron 3181 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.5590. Min Act: -0.0000

Data Index: 310937 (The Pile)

Max Activating Token Index: 763

Text #1

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.3535. Min Act: -0.0000

Data Index: 1964043 (The Pile)

Max Activating Token Index: 986

Text #2

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.3600. Min Act: -0.0000

Data Index: 1026743 (The Pile)

Max Activating Token Index: 389

Text #3

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.3889. Min Act: -0.0000

Data Index: 1368259 (The Pile)

Max Activating Token Index: 745

Text #4

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.3731. Min Act: -0.0000

Data Index: 1400755 (The Pile)

Max Activating Token Index: 348

Text #5

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.3857. Min Act: -0.0000

Data Index: 761751 (The Pile)

Max Activating Token Index: 621

Text #6

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.3669. Min Act: -0.0000

Data Index: 1989111 (The Pile)

Max Activating Token Index: 277

Text #7

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.3687. Min Act: -0.0000

Data Index: 542318 (The Pile)

Max Activating Token Index: 479

Text #8

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.3462. Min Act: -0.0000

Data Index: 323313 (The Pile)

Max Activating Token Index: 900

Text #9

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.3967. Min Act: -0.0000

Data Index: 886565 (The Pile)

Max Activating Token Index: 714

Text #10

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.3377. Min Act: -0.0000

Data Index: 233886 (The Pile)

Max Activating Token Index: 1008

Text #11

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.3563. Min Act: -0.0000

Data Index: 696489 (The Pile)

Max Activating Token Index: 488

Text #12

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.3675. Min Act: -0.0000

Data Index: 851160 (The Pile)

Max Activating Token Index: 124

Text #13

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.3468. Min Act: -0.0000

Data Index: 1561732 (The Pile)

Max Activating Token Index: 614

Text #14

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.3317. Min Act: -0.0000

Data Index: 464436 (The Pile)

Max Activating Token Index: 534

Text #15

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.3396. Min Act: -0.0000

Data Index: 1453063 (The Pile)

Max Activating Token Index: 183

Text #16

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.3360. Min Act: -0.0000

Data Index: 77012 (The Pile)

Max Activating Token Index: 738

Text #17

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.3274. Min Act: -0.0000

Data Index: 578907 (The Pile)

Max Activating Token Index: 930

Text #18

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.3480. Min Act: -0.0000

Data Index: 417928 (The Pile)

Max Activating Token Index: 382

Text #19

Max Range: 0.5590. Min Range: -0.5590

Max Act: 0.3186. Min Act: -0.0000

Data Index: 550591 (The Pile)

Max Activating Token Index: 831