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

Dataset: The Pile

Neuron 3415 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: 0.8638. Min Range: -0.8638

Max Act: 0.7065. Min Act: -0.0000

Data Index: 64908 (The Pile)

Max Activating Token Index: 349

Text #1

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.7984. Min Act: -0.0000

Data Index: 1109052 (The Pile)

Max Activating Token Index: 207

Text #2

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.7334. Min Act: -0.0000

Data Index: 411134 (The Pile)

Max Activating Token Index: 443

Text #3

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.6779. Min Act: -0.0000

Data Index: 1949287 (The Pile)

Max Activating Token Index: 157

Text #4

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.6935. Min Act: -0.0000

Data Index: 425950 (The Pile)

Max Activating Token Index: 811

Text #5

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.7045. Min Act: -0.0000

Data Index: 279767 (The Pile)

Max Activating Token Index: 136

Text #6

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.7775. Min Act: -0.0000

Data Index: 276129 (The Pile)

Max Activating Token Index: 183

Text #7

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.8638. Min Act: -0.0000

Data Index: 430607 (The Pile)

Max Activating Token Index: 939

Text #8

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.7017. Min Act: -0.0000

Data Index: 1594579 (The Pile)

Max Activating Token Index: 496

Text #9

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.8408. Min Act: -0.0000

Data Index: 188379 (The Pile)

Max Activating Token Index: 1005

Text #10

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.7326. Min Act: -0.0000

Data Index: 1601483 (The Pile)

Max Activating Token Index: 950

Text #11

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.6853. Min Act: -0.0000

Data Index: 857852 (The Pile)

Max Activating Token Index: 998

Text #12

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.6607. Min Act: -0.0000

Data Index: 612802 (The Pile)

Max Activating Token Index: 414

Text #13

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.6659. Min Act: -0.0000

Data Index: 888069 (The Pile)

Max Activating Token Index: 142

Text #14

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.7201. Min Act: -0.0000

Data Index: 603406 (The Pile)

Max Activating Token Index: 238

Text #15

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.7760. Min Act: -0.0000

Data Index: 36738 (The Pile)

Max Activating Token Index: 732

Text #16

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.6045. Min Act: -0.0000

Data Index: 1244827 (The Pile)

Max Activating Token Index: 470

Text #17

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.6004. Min Act: -0.0000

Data Index: 1648252 (The Pile)

Max Activating Token Index: 797

Text #18

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.6220. Min Act: -0.0000

Data Index: 1559217 (The Pile)

Max Activating Token Index: 400

Text #19

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.5777. Min Act: -0.0000

Data Index: 1895062 (The Pile)

Max Activating Token Index: 951