Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 810 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.8611. Min Act: -0.0000

Data Index: 1593598 (The Pile)

Max Activating Token Index: 845

Text #1

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.8109. Min Act: -0.0000

Data Index: 674845 (The Pile)

Max Activating Token Index: 594

Text #2

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.8317. Min Act: -0.0000

Data Index: 90422 (The Pile)

Max Activating Token Index: 347

Text #3

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.7572. Min Act: -0.0000

Data Index: 1202331 (The Pile)

Max Activating Token Index: 117

Text #4

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.7754. Min Act: -0.0000

Data Index: 889360 (The Pile)

Max Activating Token Index: 844

Text #5

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.7856. Min Act: -0.0000

Data Index: 1067273 (The Pile)

Max Activating Token Index: 73

Text #6

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.7158. Min Act: -0.0000

Data Index: 65869 (The Pile)

Max Activating Token Index: 833

Text #7

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.7195. Min Act: -0.0000

Data Index: 1984348 (The Pile)

Max Activating Token Index: 95

Text #8

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6730. Min Act: -0.0000

Data Index: 770221 (The Pile)

Max Activating Token Index: 611

Text #9

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6810. Min Act: -0.0000

Data Index: 1236308 (The Pile)

Max Activating Token Index: 915

Text #10

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6564. Min Act: -0.0000

Data Index: 181912 (The Pile)

Max Activating Token Index: 418

Text #11

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6761. Min Act: -0.0000

Data Index: 455952 (The Pile)

Max Activating Token Index: 390

Text #12

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6546. Min Act: -0.0000

Data Index: 1774600 (The Pile)

Max Activating Token Index: 907

Text #13

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6499. Min Act: -0.0000

Data Index: 950167 (The Pile)

Max Activating Token Index: 714

Text #14

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6688. Min Act: -0.0000

Data Index: 387521 (The Pile)

Max Activating Token Index: 104

Text #15

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6449. Min Act: -0.0000

Data Index: 1191388 (The Pile)

Max Activating Token Index: 795

Text #16

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6532. Min Act: -0.0000

Data Index: 1008279 (The Pile)

Max Activating Token Index: 56

Text #17

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6550. Min Act: -0.0000

Data Index: 919242 (The Pile)

Max Activating Token Index: 488

Text #18

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6065. Min Act: -0.0000

Data Index: 302122 (The Pile)

Max Activating Token Index: 75

Text #19

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6263. Min Act: -0.0000

Data Index: 915846 (The Pile)

Max Activating Token Index: 868