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

Dataset: The Pile

Neuron 5069 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: 0.3710. Min Range: -0.3710

Max Act: 0.3710. Min Act: -0.0000

Data Index: 1363870 (The Pile)

Max Activating Token Index: 496

Text #1

Max Range: 0.3710. Min Range: -0.3710

Max Act: 0.3360. Min Act: -0.0000

Data Index: 1005101 (The Pile)

Max Activating Token Index: 792

Text #2

Max Range: 0.3710. Min Range: -0.3710

Max Act: 0.3255. Min Act: -0.0000

Data Index: 822721 (The Pile)

Max Activating Token Index: 121

Text #3

Max Range: 0.3710. Min Range: -0.3710

Max Act: 0.2714. Min Act: -0.0000

Data Index: 1972718 (The Pile)

Max Activating Token Index: 60

Text #4

Max Range: 0.3710. Min Range: -0.3710

Max Act: 0.2695. Min Act: -0.0000

Data Index: 1913572 (The Pile)

Max Activating Token Index: 832

Text #5

Max Range: 0.3710. Min Range: -0.3710

Max Act: 0.2534. Min Act: -0.0000

Data Index: 1102617 (The Pile)

Max Activating Token Index: 971

Text #6

Max Range: 0.3710. Min Range: -0.3710

Max Act: 0.2730. Min Act: -0.0000

Data Index: 333544 (The Pile)

Max Activating Token Index: 990

Text #7

Max Range: 0.3710. Min Range: -0.3710

Max Act: 0.2617. Min Act: -0.0000

Data Index: 1982722 (The Pile)

Max Activating Token Index: 578

Text #8

Max Range: 0.3710. Min Range: -0.3710

Max Act: 0.2631. Min Act: -0.0000

Data Index: 1734297 (The Pile)

Max Activating Token Index: 920

Text #9

Max Range: 0.3710. Min Range: -0.3710

Max Act: 0.2546. Min Act: -0.0000

Data Index: 1477150 (The Pile)

Max Activating Token Index: 638

Text #10

Max Range: 0.3710. Min Range: -0.3710

Max Act: 0.2456. Min Act: -0.0000

Data Index: 1311838 (The Pile)

Max Activating Token Index: 31

Text #11

Max Range: 0.3710. Min Range: -0.3710

Max Act: 0.2434. Min Act: -0.0000

Data Index: 1455342 (The Pile)

Max Activating Token Index: 475

Text #12

Max Range: 0.3710. Min Range: -0.3710

Max Act: 0.2348. Min Act: -0.0000

Data Index: 1335496 (The Pile)

Max Activating Token Index: 599

Text #13

Max Range: 0.3710. Min Range: -0.3710

Max Act: 0.2382. Min Act: -0.0000

Data Index: 297300 (The Pile)

Max Activating Token Index: 358

Text #14

Max Range: 0.3710. Min Range: -0.3710

Max Act: 0.2301. Min Act: -0.0000

Data Index: 1552779 (The Pile)

Max Activating Token Index: 278

Text #15

Max Range: 0.3710. Min Range: -0.3710

Max Act: 0.2362. Min Act: -0.0000

Data Index: 839138 (The Pile)

Max Activating Token Index: 482

Text #16

Max Range: 0.3710. Min Range: -0.3710

Max Act: 0.2431. Min Act: -0.0000

Data Index: 530500 (The Pile)

Max Activating Token Index: 654

Text #17

Max Range: 0.3710. Min Range: -0.3710

Max Act: 0.2264. Min Act: -0.0000

Data Index: 235633 (The Pile)

Max Activating Token Index: 974

Text #18

Max Range: 0.3710. Min Range: -0.3710

Max Act: 0.2284. Min Act: -0.0000

Data Index: 699484 (The Pile)

Max Activating Token Index: 836

Text #19

Max Range: 0.3710. Min Range: -0.3710

Max Act: 0.2282. Min Act: -0.0000

Data Index: 1514329 (The Pile)

Max Activating Token Index: 586