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

Dataset: The Pile

Neuron 1357 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: 1.2379. Min Range: -1.2379

Max Act: 1.2379. Min Act: -0.0000

Data Index: 1984113 (The Pile)

Max Activating Token Index: 410

Text #1

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.7651. Min Act: -0.0000

Data Index: 136684 (The Pile)

Max Activating Token Index: 371

Text #2

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.7544. Min Act: -0.0000

Data Index: 251552 (The Pile)

Max Activating Token Index: 441

Text #3

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.6808. Min Act: -0.0000

Data Index: 1264396 (The Pile)

Max Activating Token Index: 781

Text #4

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.6906. Min Act: -0.0000

Data Index: 1924220 (The Pile)

Max Activating Token Index: 10

Text #5

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.6906. Min Act: -0.0000

Data Index: 764947 (The Pile)

Max Activating Token Index: 759

Text #6

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.5315. Min Act: -0.0000

Data Index: 1923128 (The Pile)

Max Activating Token Index: 54

Text #7

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.6091. Min Act: -0.0000

Data Index: 531269 (The Pile)

Max Activating Token Index: 22

Text #8

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.6005. Min Act: -0.0000

Data Index: 99494 (The Pile)

Max Activating Token Index: 18

Text #9

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.6114. Min Act: -0.0000

Data Index: 813832 (The Pile)

Max Activating Token Index: 105

Text #10

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.6055. Min Act: -0.0000

Data Index: 1045236 (The Pile)

Max Activating Token Index: 742

Text #11

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.5795. Min Act: -0.0000

Data Index: 1571490 (The Pile)

Max Activating Token Index: 18

Text #12

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.5357. Min Act: -0.0000

Data Index: 724155 (The Pile)

Max Activating Token Index: 630

Text #13

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.5754. Min Act: -0.0000

Data Index: 1163159 (The Pile)

Max Activating Token Index: 251

Text #14

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.6508. Min Act: -0.0000

Data Index: 794181 (The Pile)

Max Activating Token Index: 725

Text #15

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.5242. Min Act: -0.0000

Data Index: 1537874 (The Pile)

Max Activating Token Index: 22

Text #16

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.5516. Min Act: -0.0000

Data Index: 1758607 (The Pile)

Max Activating Token Index: 19

Text #17

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.5401. Min Act: -0.0000

Data Index: 1901850 (The Pile)

Max Activating Token Index: 184

Text #18

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.5812. Min Act: -0.0000

Data Index: 1286007 (The Pile)

Max Activating Token Index: 472

Text #19

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.5360. Min Act: -0.0000

Data Index: 595340 (The Pile)

Max Activating Token Index: 23