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

Dataset: The Pile

Neuron 5047 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: 1.2323. Min Range: -1.2323

Max Act: 1.2323. Min Act: -0.0000

Data Index: 239405 (The Pile)

Max Activating Token Index: 531

Text #1

Max Range: 1.2323. Min Range: -1.2323

Max Act: 1.1948. Min Act: -0.0000

Data Index: 1915417 (The Pile)

Max Activating Token Index: 82

Text #2

Max Range: 1.2323. Min Range: -1.2323

Max Act: 1.1642. Min Act: -0.0000

Data Index: 608916 (The Pile)

Max Activating Token Index: 159

Text #3

Max Range: 1.2323. Min Range: -1.2323

Max Act: 1.0503. Min Act: -0.0000

Data Index: 1986680 (The Pile)

Max Activating Token Index: 102

Text #4

Max Range: 1.2323. Min Range: -1.2323

Max Act: 1.0483. Min Act: -0.0000

Data Index: 1693007 (The Pile)

Max Activating Token Index: 171

Text #5

Max Range: 1.2323. Min Range: -1.2323

Max Act: 1.0198. Min Act: -0.0000

Data Index: 493157 (The Pile)

Max Activating Token Index: 532

Text #6

Max Range: 1.2323. Min Range: -1.2323

Max Act: 1.0582. Min Act: -0.0000

Data Index: 1541233 (The Pile)

Max Activating Token Index: 592

Text #7

Max Range: 1.2323. Min Range: -1.2323

Max Act: 1.0008. Min Act: -0.0000

Data Index: 833168 (The Pile)

Max Activating Token Index: 320

Text #8

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.9698. Min Act: -0.0000

Data Index: 773154 (The Pile)

Max Activating Token Index: 706

Text #9

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.8611. Min Act: -0.0000

Data Index: 1378079 (The Pile)

Max Activating Token Index: 812

Text #10

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.9313. Min Act: -0.0000

Data Index: 1258969 (The Pile)

Max Activating Token Index: 26

Text #11

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.9327. Min Act: -0.0000

Data Index: 1641768 (The Pile)

Max Activating Token Index: 693

Text #12

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.9283. Min Act: -0.0000

Data Index: 1415035 (The Pile)

Max Activating Token Index: 379

Text #13

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.9163. Min Act: -0.0000

Data Index: 576427 (The Pile)

Max Activating Token Index: 645

Text #14

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.8468. Min Act: -0.0000

Data Index: 264495 (The Pile)

Max Activating Token Index: 478

Text #15

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.9137. Min Act: -0.0000

Data Index: 171170 (The Pile)

Max Activating Token Index: 972

Text #16

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.9266. Min Act: -0.0000

Data Index: 751995 (The Pile)

Max Activating Token Index: 299

Text #17

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.8694. Min Act: -0.0000

Data Index: 1079998 (The Pile)

Max Activating Token Index: 495

Text #18

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.9254. Min Act: -0.0000

Data Index: 696955 (The Pile)

Max Activating Token Index: 999

Text #19

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.8187. Min Act: -0.0000

Data Index: 300824 (The Pile)

Max Activating Token Index: 30