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

Dataset: The Pile

Neuron 1353 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: 0.7945. Min Range: -0.7945

Max Act: 0.7945. Min Act: -0.0000

Data Index: 858611 (The Pile)

Max Activating Token Index: 602

Text #1

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6711. Min Act: -0.0000

Data Index: 202596 (The Pile)

Max Activating Token Index: 543

Text #2

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.7027. Min Act: -0.0000

Data Index: 151828 (The Pile)

Max Activating Token Index: 945

Text #3

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6717. Min Act: -0.0000

Data Index: 1804582 (The Pile)

Max Activating Token Index: 723

Text #4

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6586. Min Act: -0.0000

Data Index: 287765 (The Pile)

Max Activating Token Index: 205

Text #5

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6817. Min Act: -0.0000

Data Index: 957412 (The Pile)

Max Activating Token Index: 129

Text #6

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6512. Min Act: -0.0000

Data Index: 742090 (The Pile)

Max Activating Token Index: 565

Text #7

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6285. Min Act: -0.0000

Data Index: 638120 (The Pile)

Max Activating Token Index: 42

Text #8

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6479. Min Act: -0.0000

Data Index: 508921 (The Pile)

Max Activating Token Index: 613

Text #9

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6449. Min Act: -0.0000

Data Index: 856508 (The Pile)

Max Activating Token Index: 92

Text #10

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6509. Min Act: -0.0000

Data Index: 1259241 (The Pile)

Max Activating Token Index: 852

Text #11

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6386. Min Act: -0.0000

Data Index: 1866518 (The Pile)

Max Activating Token Index: 229

Text #12

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6224. Min Act: -0.0000

Data Index: 802160 (The Pile)

Max Activating Token Index: 826

Text #13

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6149. Min Act: -0.0000

Data Index: 906770 (The Pile)

Max Activating Token Index: 595

Text #14

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.5968. Min Act: -0.0000

Data Index: 530348 (The Pile)

Max Activating Token Index: 956

Text #15

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6150. Min Act: -0.0000

Data Index: 1368445 (The Pile)

Max Activating Token Index: 419

Text #16

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6359. Min Act: -0.0000

Data Index: 345430 (The Pile)

Max Activating Token Index: 442

Text #17

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6271. Min Act: -0.0000

Data Index: 1211591 (The Pile)

Max Activating Token Index: 816

Text #18

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.5877. Min Act: -0.0000

Data Index: 1700081 (The Pile)

Max Activating Token Index: 199

Text #19

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.5432. Min Act: -0.0000

Data Index: 1730289 (The Pile)

Max Activating Token Index: 1018