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

Dataset: The Pile

Neuron 4314 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.3306. Min Act: -0.0000

Data Index: 1875280 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.4058. Min Act: -0.0000

Data Index: 1581036 (The Pile)

Max Activating Token Index: 780

Text #2

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.4104. Min Act: -0.0000

Data Index: 1338739 (The Pile)

Max Activating Token Index: 34

Text #3

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.3737. Min Act: -0.0000

Data Index: 1329421 (The Pile)

Max Activating Token Index: 263

Text #4

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.3248. Min Act: -0.0000

Data Index: 446174 (The Pile)

Max Activating Token Index: 7

Text #5

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.3420. Min Act: -0.0000

Data Index: 1027512 (The Pile)

Max Activating Token Index: 215

Text #6

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.3711. Min Act: -0.0000

Data Index: 1498015 (The Pile)

Max Activating Token Index: 129

Text #7

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.2960. Min Act: -0.0000

Data Index: 1105979 (The Pile)

Max Activating Token Index: 353

Text #8

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.2868. Min Act: -0.0000

Data Index: 1211556 (The Pile)

Max Activating Token Index: 344

Text #9

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.2140. Min Act: -0.0000

Data Index: 61480 (The Pile)

Max Activating Token Index: 859

Text #10

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.2154. Min Act: -0.0000

Data Index: 1202931 (The Pile)

Max Activating Token Index: 46

Text #11

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.1892. Min Act: -0.0000

Data Index: 175495 (The Pile)

Max Activating Token Index: 570

Text #12

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.1851. Min Act: -0.0000

Data Index: 1983133 (The Pile)

Max Activating Token Index: 274

Text #13

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.2056. Min Act: -0.0000

Data Index: 814698 (The Pile)

Max Activating Token Index: 147

Text #14

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.2297. Min Act: -0.0000

Data Index: 1037696 (The Pile)

Max Activating Token Index: 5

Text #15

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.2323. Min Act: -0.0000

Data Index: 1063118 (The Pile)

Max Activating Token Index: 307

Text #16

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.0975. Min Act: -0.0000

Data Index: 1243638 (The Pile)

Max Activating Token Index: 375

Text #17

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.1326. Min Act: -0.0000

Data Index: 584267 (The Pile)

Max Activating Token Index: 801

Text #18

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.1789. Min Act: -0.0000

Data Index: 1274376 (The Pile)

Max Activating Token Index: 455

Text #19

Max Range: 1.4104. Min Range: -1.4104

Max Act: 1.2054. Min Act: -0.0000

Data Index: 1075756 (The Pile)

Max Activating Token Index: 99