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

Dataset: The Pile

Neuron 2477 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2878. Min Act: -0.0000

Data Index: 1613134 (The Pile)

Max Activating Token Index: 135

Text #1

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2814. Min Act: -0.0000

Data Index: 1697635 (The Pile)

Max Activating Token Index: 110

Text #2

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2696. Min Act: -0.0000

Data Index: 89928 (The Pile)

Max Activating Token Index: 880

Text #3

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2746. Min Act: -0.0000

Data Index: 484582 (The Pile)

Max Activating Token Index: 257

Text #4

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2699. Min Act: -0.0000

Data Index: 1748618 (The Pile)

Max Activating Token Index: 849

Text #5

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2605. Min Act: -0.0000

Data Index: 262847 (The Pile)

Max Activating Token Index: 238

Text #6

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2515. Min Act: -0.0000

Data Index: 22309 (The Pile)

Max Activating Token Index: 230

Text #7

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2461. Min Act: -0.0000

Data Index: 513743 (The Pile)

Max Activating Token Index: 444

Text #8

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2463. Min Act: -0.0000

Data Index: 1640310 (The Pile)

Max Activating Token Index: 692

Text #9

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2392. Min Act: -0.0000

Data Index: 875372 (The Pile)

Max Activating Token Index: 744

Text #10

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2377. Min Act: -0.0000

Data Index: 1144114 (The Pile)

Max Activating Token Index: 876

Text #11

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2340. Min Act: -0.0000

Data Index: 182870 (The Pile)

Max Activating Token Index: 528

Text #12

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2345. Min Act: -0.0000

Data Index: 1221139 (The Pile)

Max Activating Token Index: 786

Text #13

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2385. Min Act: -0.0000

Data Index: 1745297 (The Pile)

Max Activating Token Index: 763

Text #14

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2414. Min Act: -0.0000

Data Index: 1853500 (The Pile)

Max Activating Token Index: 63

Text #15

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2274. Min Act: -0.0000

Data Index: 1542951 (The Pile)

Max Activating Token Index: 536

Text #16

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2119. Min Act: -0.0000

Data Index: 34701 (The Pile)

Max Activating Token Index: 645

Text #17

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2261. Min Act: -0.0000

Data Index: 1179823 (The Pile)

Max Activating Token Index: 248

Text #18

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2593. Min Act: -0.0000

Data Index: 509000 (The Pile)

Max Activating Token Index: 878

Text #19

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2191. Min Act: -0.0000

Data Index: 1530591 (The Pile)

Max Activating Token Index: 203