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

Dataset: The Pile

Neuron 3586 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.3216. Min Act: -0.0000

Data Index: 1121957 (The Pile)

Max Activating Token Index: 486

Text #1

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.3102. Min Act: -0.0000

Data Index: 76654 (The Pile)

Max Activating Token Index: 980

Text #2

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.1446. Min Act: -0.0000

Data Index: 1003975 (The Pile)

Max Activating Token Index: 303

Text #3

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.1120. Min Act: 0.0000

Data Index: 109436 (The Pile)

Max Activating Token Index: 614

Text #4

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.0705. Min Act: -0.0000

Data Index: 1995485 (The Pile)

Max Activating Token Index: 218

Text #5

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.0627. Min Act: -0.0000

Data Index: 752059 (The Pile)

Max Activating Token Index: 959

Text #6

Max Range: 1.3216. Min Range: -1.3216

Max Act: 0.9994. Min Act: -0.0000

Data Index: 493828 (The Pile)

Max Activating Token Index: 766

Text #7

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.1048. Min Act: -0.0000

Data Index: 486579 (The Pile)

Max Activating Token Index: 419

Text #8

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.0999. Min Act: -0.0000

Data Index: 1765533 (The Pile)

Max Activating Token Index: 174

Text #9

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.0616. Min Act: -0.0000

Data Index: 472339 (The Pile)

Max Activating Token Index: 430

Text #10

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.0862. Min Act: -0.0000

Data Index: 1194701 (The Pile)

Max Activating Token Index: 311

Text #11

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.0793. Min Act: -0.0000

Data Index: 363719 (The Pile)

Max Activating Token Index: 465

Text #12

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.1373. Min Act: -0.0000

Data Index: 181201 (The Pile)

Max Activating Token Index: 284

Text #13

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.1170. Min Act: -0.0000

Data Index: 1666231 (The Pile)

Max Activating Token Index: 176

Text #14

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.0837. Min Act: -0.0000

Data Index: 1657733 (The Pile)

Max Activating Token Index: 179

Text #15

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.0375. Min Act: -0.0000

Data Index: 478255 (The Pile)

Max Activating Token Index: 535

Text #16

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.0347. Min Act: 0.0000

Data Index: 704159 (The Pile)

Max Activating Token Index: 612

Text #17

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.0274. Min Act: 0.0000

Data Index: 152491 (The Pile)

Max Activating Token Index: 560

Text #18

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.0098. Min Act: 0.0000

Data Index: 1229491 (The Pile)

Max Activating Token Index: 964

Text #19

Max Range: 1.3216. Min Range: -1.3216

Max Act: 0.9920. Min Act: -0.0000

Data Index: 1928054 (The Pile)

Max Activating Token Index: 128