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

Dataset: The Pile

Neuron 961 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.8876. Min Act: -0.0000

Data Index: 1096995 (The Pile)

Max Activating Token Index: 383

Text #1

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.9084. Min Act: -0.0000

Data Index: 1418211 (The Pile)

Max Activating Token Index: 454

Text #2

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.8057. Min Act: -0.0000

Data Index: 1464045 (The Pile)

Max Activating Token Index: 88

Text #3

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.7564. Min Act: -0.0000

Data Index: 894072 (The Pile)

Max Activating Token Index: 443

Text #4

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.6933. Min Act: -0.0000

Data Index: 1793666 (The Pile)

Max Activating Token Index: 663

Text #5

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.7092. Min Act: -0.0000

Data Index: 1398623 (The Pile)

Max Activating Token Index: 404

Text #6

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.7045. Min Act: -0.0000

Data Index: 1555749 (The Pile)

Max Activating Token Index: 370

Text #7

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.6666. Min Act: -0.0000

Data Index: 1638031 (The Pile)

Max Activating Token Index: 726

Text #8

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.6989. Min Act: -0.0000

Data Index: 1020832 (The Pile)

Max Activating Token Index: 104

Text #9

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.7054. Min Act: -0.0000

Data Index: 1148456 (The Pile)

Max Activating Token Index: 656

Text #10

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.6566. Min Act: -0.0000

Data Index: 133728 (The Pile)

Max Activating Token Index: 251

Text #11

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.6510. Min Act: -0.0000

Data Index: 162930 (The Pile)

Max Activating Token Index: 338

Text #12

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.5664. Min Act: 0.0000

Data Index: 311059 (The Pile)

Max Activating Token Index: 110

Text #13

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.6345. Min Act: -0.0000

Data Index: 1958045 (The Pile)

Max Activating Token Index: 26

Text #14

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.6732. Min Act: -0.0000

Data Index: 1600352 (The Pile)

Max Activating Token Index: 652

Text #15

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.6634. Min Act: 0.0000

Data Index: 1917483 (The Pile)

Max Activating Token Index: 35

Text #16

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.6426. Min Act: 0.0000

Data Index: 838996 (The Pile)

Max Activating Token Index: 773

Text #17

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.6075. Min Act: -0.0000

Data Index: 1852253 (The Pile)

Max Activating Token Index: 1016

Text #18

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.6663. Min Act: -0.0000

Data Index: 224272 (The Pile)

Max Activating Token Index: 816

Text #19

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.6145. Min Act: -0.0000

Data Index: 1050320 (The Pile)

Max Activating Token Index: 681