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

Dataset: The Pile

Neuron 1685 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: 0.2923. Min Range: -0.2923

Max Act: 0.2882. Min Act: -0.0000

Data Index: 436417 (The Pile)

Max Activating Token Index: 927

Text #1

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.2923. Min Act: -0.0000

Data Index: 1544305 (The Pile)

Max Activating Token Index: 96

Text #2

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.2725. Min Act: -0.0000

Data Index: 343716 (The Pile)

Max Activating Token Index: 495

Text #3

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.2673. Min Act: -0.0000

Data Index: 1971085 (The Pile)

Max Activating Token Index: 158

Text #4

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.2369. Min Act: -0.0000

Data Index: 290293 (The Pile)

Max Activating Token Index: 650

Text #5

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.2302. Min Act: -0.0000

Data Index: 1453756 (The Pile)

Max Activating Token Index: 351

Text #6

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.2572. Min Act: -0.0000

Data Index: 946009 (The Pile)

Max Activating Token Index: 784

Text #7

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.2302. Min Act: -0.0000

Data Index: 241212 (The Pile)

Max Activating Token Index: 548

Text #8

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.2134. Min Act: -0.0000

Data Index: 270473 (The Pile)

Max Activating Token Index: 322

Text #9

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.2100. Min Act: -0.0000

Data Index: 1434218 (The Pile)

Max Activating Token Index: 354

Text #10

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.2080. Min Act: -0.0000

Data Index: 83171 (The Pile)

Max Activating Token Index: 989

Text #11

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.2073. Min Act: -0.0000

Data Index: 1503817 (The Pile)

Max Activating Token Index: 583

Text #12

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.1986. Min Act: -0.0000

Data Index: 1976437 (The Pile)

Max Activating Token Index: 563

Text #13

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.2060. Min Act: -0.0000

Data Index: 1145349 (The Pile)

Max Activating Token Index: 105

Text #14

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.2096. Min Act: -0.0000

Data Index: 261777 (The Pile)

Max Activating Token Index: 704

Text #15

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.1987. Min Act: -0.0000

Data Index: 1371980 (The Pile)

Max Activating Token Index: 615

Text #16

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.2046. Min Act: -0.0000

Data Index: 1914896 (The Pile)

Max Activating Token Index: 754

Text #17

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.2015. Min Act: -0.0000

Data Index: 1325780 (The Pile)

Max Activating Token Index: 76

Text #18

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.1944. Min Act: -0.0000

Data Index: 701575 (The Pile)

Max Activating Token Index: 211

Text #19

Max Range: 0.2923. Min Range: -0.2923

Max Act: 0.1863. Min Act: -0.0000

Data Index: 836113 (The Pile)

Max Activating Token Index: 1013