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

Dataset: The Pile

Neuron 2131 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: 0.8421. Min Range: -0.8421

Max Act: 0.8268. Min Act: -0.0000

Data Index: 184158 (The Pile)

Max Activating Token Index: 12

Text #1

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.8421. Min Act: -0.0000

Data Index: 670283 (The Pile)

Max Activating Token Index: 652

Text #2

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.7599. Min Act: -0.0000

Data Index: 1708132 (The Pile)

Max Activating Token Index: 435

Text #3

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.7218. Min Act: 0.0000

Data Index: 1762022 (The Pile)

Max Activating Token Index: 667

Text #4

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.7410. Min Act: -0.0000

Data Index: 1913208 (The Pile)

Max Activating Token Index: 50

Text #5

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.7185. Min Act: -0.0000

Data Index: 1512248 (The Pile)

Max Activating Token Index: 32

Text #6

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.6534. Min Act: -0.0000

Data Index: 1549657 (The Pile)

Max Activating Token Index: 708

Text #7

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.6655. Min Act: -0.0000

Data Index: 967556 (The Pile)

Max Activating Token Index: 17

Text #8

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.6880. Min Act: -0.0000

Data Index: 843757 (The Pile)

Max Activating Token Index: 941

Text #9

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.6516. Min Act: -0.0000

Data Index: 1756126 (The Pile)

Max Activating Token Index: 944

Text #10

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.6650. Min Act: -0.0000

Data Index: 511084 (The Pile)

Max Activating Token Index: 417

Text #11

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.6639. Min Act: -0.0000

Data Index: 1742236 (The Pile)

Max Activating Token Index: 264

Text #12

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.6473. Min Act: -0.0000

Data Index: 1814358 (The Pile)

Max Activating Token Index: 152

Text #13

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.6259. Min Act: -0.0000

Data Index: 1966272 (The Pile)

Max Activating Token Index: 334

Text #14

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.6654. Min Act: -0.0000

Data Index: 1780802 (The Pile)

Max Activating Token Index: 57

Text #15

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.6244. Min Act: -0.0000

Data Index: 683595 (The Pile)

Max Activating Token Index: 385

Text #16

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.6397. Min Act: -0.0000

Data Index: 835017 (The Pile)

Max Activating Token Index: 14

Text #17

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.6473. Min Act: -0.0000

Data Index: 1577030 (The Pile)

Max Activating Token Index: 641

Text #18

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.6126. Min Act: -0.0000

Data Index: 561150 (The Pile)

Max Activating Token Index: 13

Text #19

Max Range: 0.8421. Min Range: -0.8421

Max Act: 0.6488. Min Act: -0.0000

Data Index: 1583758 (The Pile)

Max Activating Token Index: 822