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

Dataset: The Pile

Neuron 5065 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: 1.0141. Min Range: -1.0141

Max Act: 1.0141. Min Act: -0.0000

Data Index: 942597 (The Pile)

Max Activating Token Index: 39

Text #1

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.6418. Min Act: -0.0000

Data Index: 441553 (The Pile)

Max Activating Token Index: 835

Text #2

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.7057. Min Act: -0.0000

Data Index: 231852 (The Pile)

Max Activating Token Index: 771

Text #3

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.5620. Min Act: -0.0000

Data Index: 357110 (The Pile)

Max Activating Token Index: 868

Text #4

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.5027. Min Act: -0.0000

Data Index: 1379753 (The Pile)

Max Activating Token Index: 395

Text #5

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.4773. Min Act: -0.0000

Data Index: 1656927 (The Pile)

Max Activating Token Index: 990

Text #6

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.5109. Min Act: -0.0000

Data Index: 354826 (The Pile)

Max Activating Token Index: 145

Text #7

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.4479. Min Act: -0.0000

Data Index: 827485 (The Pile)

Max Activating Token Index: 178

Text #8

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.4279. Min Act: -0.0000

Data Index: 902450 (The Pile)

Max Activating Token Index: 613

Text #9

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.3930. Min Act: -0.0000

Data Index: 1131958 (The Pile)

Max Activating Token Index: 553

Text #10

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.3958. Min Act: -0.0000

Data Index: 1562414 (The Pile)

Max Activating Token Index: 689

Text #11

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.4514. Min Act: -0.0000

Data Index: 325645 (The Pile)

Max Activating Token Index: 967

Text #12

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.3941. Min Act: -0.0000

Data Index: 202976 (The Pile)

Max Activating Token Index: 966

Text #13

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.4035. Min Act: -0.0000

Data Index: 97821 (The Pile)

Max Activating Token Index: 20

Text #14

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.3949. Min Act: -0.0000

Data Index: 954069 (The Pile)

Max Activating Token Index: 177

Text #15

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.4081. Min Act: -0.0000

Data Index: 616653 (The Pile)

Max Activating Token Index: 172

Text #16

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.3870. Min Act: -0.0000

Data Index: 1221363 (The Pile)

Max Activating Token Index: 923

Text #17

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.3719. Min Act: -0.0000

Data Index: 1294345 (The Pile)

Max Activating Token Index: 44

Text #18

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.3764. Min Act: -0.0000

Data Index: 1653342 (The Pile)

Max Activating Token Index: 848

Text #19

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.4022. Min Act: -0.0000

Data Index: 617851 (The Pile)

Max Activating Token Index: 161