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

Dataset: The Pile

Neuron 4934 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: 3.7426. Min Range: -3.7426

Max Act: 3.7284. Min Act: -0.0000

Data Index: 424140 (The Pile)

Max Activating Token Index: 98

Text #1

Max Range: 3.7426. Min Range: -3.7426

Max Act: 3.7426. Min Act: -0.0000

Data Index: 1625106 (The Pile)

Max Activating Token Index: 61

Text #2

Max Range: 3.7426. Min Range: -3.7426

Max Act: 3.4758. Min Act: -0.0000

Data Index: 965563 (The Pile)

Max Activating Token Index: 87

Text #3

Max Range: 3.7426. Min Range: -3.7426

Max Act: 3.1247. Min Act: -0.0000

Data Index: 1192377 (The Pile)

Max Activating Token Index: 148

Text #4

Max Range: 3.7426. Min Range: -3.7426

Max Act: 3.5486. Min Act: -0.0000

Data Index: 1491794 (The Pile)

Max Activating Token Index: 467

Text #5

Max Range: 3.7426. Min Range: -3.7426

Max Act: 3.0720. Min Act: -0.0000

Data Index: 1805399 (The Pile)

Max Activating Token Index: 327

Text #6

Max Range: 3.7426. Min Range: -3.7426

Max Act: 3.1809. Min Act: -0.0000

Data Index: 1124049 (The Pile)

Max Activating Token Index: 297

Text #7

Max Range: 3.7426. Min Range: -3.7426

Max Act: 2.8180. Min Act: -0.0000

Data Index: 1389601 (The Pile)

Max Activating Token Index: 154

Text #8

Max Range: 3.7426. Min Range: -3.7426

Max Act: 3.2562. Min Act: -0.0000

Data Index: 160096 (The Pile)

Max Activating Token Index: 392

Text #9

Max Range: 3.7426. Min Range: -3.7426

Max Act: 3.0849. Min Act: -0.0000

Data Index: 185710 (The Pile)

Max Activating Token Index: 889

Text #10

Max Range: 3.7426. Min Range: -3.7426

Max Act: 2.9799. Min Act: -0.0000

Data Index: 1736972 (The Pile)

Max Activating Token Index: 390

Text #11

Max Range: 3.7426. Min Range: -3.7426

Max Act: 3.2283. Min Act: -0.0000

Data Index: 1920400 (The Pile)

Max Activating Token Index: 137

Text #12

Max Range: 3.7426. Min Range: -3.7426

Max Act: 3.0622. Min Act: -0.0000

Data Index: 1043357 (The Pile)

Max Activating Token Index: 264

Text #13

Max Range: 3.7426. Min Range: -3.7426

Max Act: 3.2054. Min Act: -0.0000

Data Index: 1475852 (The Pile)

Max Activating Token Index: 95

Text #14

Max Range: 3.7426. Min Range: -3.7426

Max Act: 3.0504. Min Act: -0.0000

Data Index: 105917 (The Pile)

Max Activating Token Index: 126

Text #15

Max Range: 3.7426. Min Range: -3.7426

Max Act: 2.9060. Min Act: -0.0000

Data Index: 200442 (The Pile)

Max Activating Token Index: 582

Text #16

Max Range: 3.7426. Min Range: -3.7426

Max Act: 3.1845. Min Act: -0.0000

Data Index: 903675 (The Pile)

Max Activating Token Index: 453

Text #17

Max Range: 3.7426. Min Range: -3.7426

Max Act: 3.0405. Min Act: -0.0000

Data Index: 593906 (The Pile)

Max Activating Token Index: 328

Text #18

Max Range: 3.7426. Min Range: -3.7426

Max Act: 3.0412. Min Act: -0.0000

Data Index: 1543807 (The Pile)

Max Activating Token Index: 214

Text #19

Max Range: 3.7426. Min Range: -3.7426

Max Act: 3.1501. Min Act: -0.0000

Data Index: 1387258 (The Pile)

Max Activating Token Index: 325