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

Dataset: The Pile

Neuron 2827 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2996. Min Range: -1.2996

Max Act: 1.2996. Min Act: -0.0000

Data Index: 755247 (The Pile)

Max Activating Token Index: 491

Text #1

Max Range: 1.2996. Min Range: -1.2996

Max Act: 1.1964. Min Act: 0.0001

Data Index: 534921 (The Pile)

Max Activating Token Index: 83

Text #2

Max Range: 1.2996. Min Range: -1.2996

Max Act: 1.1846. Min Act: -0.0000

Data Index: 1151871 (The Pile)

Max Activating Token Index: 166

Text #3

Max Range: 1.2996. Min Range: -1.2996

Max Act: 1.1004. Min Act: -0.0000

Data Index: 1844213 (The Pile)

Max Activating Token Index: 693

Text #4

Max Range: 1.2996. Min Range: -1.2996

Max Act: 1.0115. Min Act: 0.0000

Data Index: 1758449 (The Pile)

Max Activating Token Index: 981

Text #5

Max Range: 1.2996. Min Range: -1.2996

Max Act: 0.9566. Min Act: -0.0000

Data Index: 1912538 (The Pile)

Max Activating Token Index: 489

Text #6

Max Range: 1.2996. Min Range: -1.2996

Max Act: 0.9091. Min Act: -0.0000

Data Index: 751681 (The Pile)

Max Activating Token Index: 359

Text #7

Max Range: 1.2996. Min Range: -1.2996

Max Act: 0.9566. Min Act: -0.0000

Data Index: 1943532 (The Pile)

Max Activating Token Index: 500

Text #8

Max Range: 1.2996. Min Range: -1.2996

Max Act: 1.0092. Min Act: -0.0000

Data Index: 179243 (The Pile)

Max Activating Token Index: 259

Text #9

Max Range: 1.2996. Min Range: -1.2996

Max Act: 0.9477. Min Act: -0.0000

Data Index: 1891448 (The Pile)

Max Activating Token Index: 397

Text #10

Max Range: 1.2996. Min Range: -1.2996

Max Act: 0.8833. Min Act: -0.0000

Data Index: 4084 (The Pile)

Max Activating Token Index: 417

Text #11

Max Range: 1.2996. Min Range: -1.2996

Max Act: 0.9026. Min Act: -0.0000

Data Index: 737194 (The Pile)

Max Activating Token Index: 135

Text #12

Max Range: 1.2996. Min Range: -1.2996

Max Act: 0.8955. Min Act: -0.0000

Data Index: 744303 (The Pile)

Max Activating Token Index: 102

Text #13

Max Range: 1.2996. Min Range: -1.2996

Max Act: 0.8882. Min Act: -0.0000

Data Index: 1945759 (The Pile)

Max Activating Token Index: 604

Text #14

Max Range: 1.2996. Min Range: -1.2996

Max Act: 0.8590. Min Act: -0.0000

Data Index: 446440 (The Pile)

Max Activating Token Index: 198

Text #15

Max Range: 1.2996. Min Range: -1.2996

Max Act: 0.8571. Min Act: 0.0000

Data Index: 440740 (The Pile)

Max Activating Token Index: 518

Text #16

Max Range: 1.2996. Min Range: -1.2996

Max Act: 0.8454. Min Act: -0.0000

Data Index: 1006783 (The Pile)

Max Activating Token Index: 830

Text #17

Max Range: 1.2996. Min Range: -1.2996

Max Act: 0.8068. Min Act: -0.0000

Data Index: 147705 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 1.2996. Min Range: -1.2996

Max Act: 0.7975. Min Act: -0.0000

Data Index: 1408647 (The Pile)

Max Activating Token Index: 819

Text #19

Max Range: 1.2996. Min Range: -1.2996

Max Act: 0.7972. Min Act: -0.0000

Data Index: 1258622 (The Pile)

Max Activating Token Index: 56