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

Dataset: The Pile

Neuron 1402 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: 1.2376. Min Range: -1.2376

Max Act: 1.2376. Min Act: -0.0000

Data Index: 480820 (The Pile)

Max Activating Token Index: 408

Text #1

Max Range: 1.2376. Min Range: -1.2376

Max Act: 1.0773. Min Act: -0.0000

Data Index: 649100 (The Pile)

Max Activating Token Index: 105

Text #2

Max Range: 1.2376. Min Range: -1.2376

Max Act: 1.0174. Min Act: -0.0000

Data Index: 104096 (The Pile)

Max Activating Token Index: 806

Text #3

Max Range: 1.2376. Min Range: -1.2376

Max Act: 1.0549. Min Act: -0.0000

Data Index: 1539219 (The Pile)

Max Activating Token Index: 634

Text #4

Max Range: 1.2376. Min Range: -1.2376

Max Act: 0.9570. Min Act: -0.0000

Data Index: 417900 (The Pile)

Max Activating Token Index: 326

Text #5

Max Range: 1.2376. Min Range: -1.2376

Max Act: 0.9525. Min Act: -0.0000

Data Index: 1014744 (The Pile)

Max Activating Token Index: 468

Text #6

Max Range: 1.2376. Min Range: -1.2376

Max Act: 0.9389. Min Act: -0.0000

Data Index: 29912 (The Pile)

Max Activating Token Index: 947

Text #7

Max Range: 1.2376. Min Range: -1.2376

Max Act: 0.8862. Min Act: -0.0000

Data Index: 1723222 (The Pile)

Max Activating Token Index: 837

Text #8

Max Range: 1.2376. Min Range: -1.2376

Max Act: 0.8311. Min Act: -0.0000

Data Index: 1974289 (The Pile)

Max Activating Token Index: 573

Text #9

Max Range: 1.2376. Min Range: -1.2376

Max Act: 0.9771. Min Act: -0.0000

Data Index: 574668 (The Pile)

Max Activating Token Index: 830

Text #10

Max Range: 1.2376. Min Range: -1.2376

Max Act: 0.9166. Min Act: -0.0000

Data Index: 55695 (The Pile)

Max Activating Token Index: 83

Text #11

Max Range: 1.2376. Min Range: -1.2376

Max Act: 0.8550. Min Act: -0.0000

Data Index: 1199973 (The Pile)

Max Activating Token Index: 181

Text #12

Max Range: 1.2376. Min Range: -1.2376

Max Act: 1.1020. Min Act: -0.0000

Data Index: 475962 (The Pile)

Max Activating Token Index: 662

Text #13

Max Range: 1.2376. Min Range: -1.2376

Max Act: 0.9021. Min Act: -0.0000

Data Index: 430950 (The Pile)

Max Activating Token Index: 640

Text #14

Max Range: 1.2376. Min Range: -1.2376

Max Act: 0.9559. Min Act: -0.0000

Data Index: 1097023 (The Pile)

Max Activating Token Index: 446

Text #15

Max Range: 1.2376. Min Range: -1.2376

Max Act: 0.7930. Min Act: -0.0000

Data Index: 1698876 (The Pile)

Max Activating Token Index: 828

Text #16

Max Range: 1.2376. Min Range: -1.2376

Max Act: 0.8679. Min Act: -0.0000

Data Index: 1104479 (The Pile)

Max Activating Token Index: 376

Text #17

Max Range: 1.2376. Min Range: -1.2376

Max Act: 0.9201. Min Act: -0.0000

Data Index: 922651 (The Pile)

Max Activating Token Index: 665

Text #18

Max Range: 1.2376. Min Range: -1.2376

Max Act: 0.9537. Min Act: -0.0000

Data Index: 153177 (The Pile)

Max Activating Token Index: 304

Text #19

Max Range: 1.2376. Min Range: -1.2376

Max Act: 0.8861. Min Act: -0.0000

Data Index: 1060500 (The Pile)

Max Activating Token Index: 234