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

Dataset: The Pile

Neuron 206 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.7249. Min Act: -0.0000

Data Index: 1847005 (The Pile)

Max Activating Token Index: 95

Text #1

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.6106. Min Act: -0.0000

Data Index: 24618 (The Pile)

Max Activating Token Index: 985

Text #2

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.5737. Min Act: -0.0000

Data Index: 626097 (The Pile)

Max Activating Token Index: 767

Text #3

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.5534. Min Act: -0.0000

Data Index: 1045286 (The Pile)

Max Activating Token Index: 30

Text #4

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.5406. Min Act: -0.0000

Data Index: 96264 (The Pile)

Max Activating Token Index: 614

Text #5

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4900. Min Act: -0.0000

Data Index: 985525 (The Pile)

Max Activating Token Index: 899

Text #6

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4625. Min Act: -0.0000

Data Index: 1239978 (The Pile)

Max Activating Token Index: 338

Text #7

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4988. Min Act: -0.0000

Data Index: 360078 (The Pile)

Max Activating Token Index: 220

Text #8

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4476. Min Act: -0.0000

Data Index: 1942532 (The Pile)

Max Activating Token Index: 162

Text #9

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4649. Min Act: -0.0000

Data Index: 662086 (The Pile)

Max Activating Token Index: 94

Text #10

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4686. Min Act: -0.0000

Data Index: 1704309 (The Pile)

Max Activating Token Index: 731

Text #11

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4710. Min Act: -0.0000

Data Index: 747682 (The Pile)

Max Activating Token Index: 203

Text #12

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4695. Min Act: -0.0000

Data Index: 1547135 (The Pile)

Max Activating Token Index: 343

Text #13

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4627. Min Act: -0.0000

Data Index: 545597 (The Pile)

Max Activating Token Index: 525

Text #14

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4765. Min Act: -0.0000

Data Index: 567939 (The Pile)

Max Activating Token Index: 333

Text #15

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4351. Min Act: -0.0000

Data Index: 1852093 (The Pile)

Max Activating Token Index: 317

Text #16

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4446. Min Act: -0.0000

Data Index: 1949172 (The Pile)

Max Activating Token Index: 142

Text #17

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4202. Min Act: -0.0000

Data Index: 792351 (The Pile)

Max Activating Token Index: 326

Text #18

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4172. Min Act: -0.0000

Data Index: 1022650 (The Pile)

Max Activating Token Index: 48

Text #19

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4142. Min Act: -0.0000

Data Index: 1599132 (The Pile)

Max Activating Token Index: 242