Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3725 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0442. Min Range: -1.0442

Max Act: 1.0442. Min Act: -0.0000

Data Index: 1051882 (The Pile)

Max Activating Token Index: 726

Text #1

Max Range: 1.0442. Min Range: -1.0442

Max Act: 0.7765. Min Act: -0.0000

Data Index: 396166 (The Pile)

Max Activating Token Index: 193

Text #2

Max Range: 1.0442. Min Range: -1.0442

Max Act: 0.7455. Min Act: -0.0000

Data Index: 1505933 (The Pile)

Max Activating Token Index: 884

Text #3

Max Range: 1.0442. Min Range: -1.0442

Max Act: 0.6820. Min Act: -0.0000

Data Index: 1080 (The Pile)

Max Activating Token Index: 505

Text #4

Max Range: 1.0442. Min Range: -1.0442

Max Act: 0.8071. Min Act: -0.0000

Data Index: 1293158 (The Pile)

Max Activating Token Index: 795

Text #5

Max Range: 1.0442. Min Range: -1.0442

Max Act: 0.5602. Min Act: -0.0001

Data Index: 850139 (The Pile)

Max Activating Token Index: 296

Text #6

Max Range: 1.0442. Min Range: -1.0442

Max Act: 0.6074. Min Act: -0.0000

Data Index: 445566 (The Pile)

Max Activating Token Index: 473

Text #7

Max Range: 1.0442. Min Range: -1.0442

Max Act: 0.6090. Min Act: -0.0000

Data Index: 1496093 (The Pile)

Max Activating Token Index: 869

Text #8

Max Range: 1.0442. Min Range: -1.0442

Max Act: 0.5587. Min Act: -0.0000

Data Index: 129360 (The Pile)

Max Activating Token Index: 342

Text #9

Max Range: 1.0442. Min Range: -1.0442

Max Act: 0.5955. Min Act: -0.0000

Data Index: 234684 (The Pile)

Max Activating Token Index: 917

Text #10

Max Range: 1.0442. Min Range: -1.0442

Max Act: 0.6160. Min Act: -0.0000

Data Index: 955698 (The Pile)

Max Activating Token Index: 896

Text #11

Max Range: 1.0442. Min Range: -1.0442

Max Act: 0.5709. Min Act: -0.0000

Data Index: 1162260 (The Pile)

Max Activating Token Index: 766

Text #12

Max Range: 1.0442. Min Range: -1.0442

Max Act: 0.5549. Min Act: -0.0000

Data Index: 437184 (The Pile)

Max Activating Token Index: 764

Text #13

Max Range: 1.0442. Min Range: -1.0442

Max Act: 0.5631. Min Act: -0.0000

Data Index: 1650903 (The Pile)

Max Activating Token Index: 348

Text #14

Max Range: 1.0442. Min Range: -1.0442

Max Act: 0.4847. Min Act: -0.0000

Data Index: 1714300 (The Pile)

Max Activating Token Index: 673

Text #15

Max Range: 1.0442. Min Range: -1.0442

Max Act: 0.6049. Min Act: -0.0000

Data Index: 1959872 (The Pile)

Max Activating Token Index: 643

Text #16

Max Range: 1.0442. Min Range: -1.0442

Max Act: 0.5065. Min Act: -0.0000

Data Index: 1789581 (The Pile)

Max Activating Token Index: 107

Text #17

Max Range: 1.0442. Min Range: -1.0442

Max Act: 0.5058. Min Act: -0.0000

Data Index: 1633239 (The Pile)

Max Activating Token Index: 291

Text #18

Max Range: 1.0442. Min Range: -1.0442

Max Act: 0.5130. Min Act: -0.0000

Data Index: 295073 (The Pile)

Max Activating Token Index: 316

Text #19

Max Range: 1.0442. Min Range: -1.0442

Max Act: 0.5288. Min Act: -0.0000

Data Index: 7908 (The Pile)

Max Activating Token Index: 183