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

Dataset: The Pile

Neuron 1101 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: 0.7758. Min Range: -0.7758

Max Act: 0.7758. Min Act: -0.0000

Data Index: 640492 (The Pile)

Max Activating Token Index: 561

Text #1

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.7417. Min Act: -0.0000

Data Index: 750909 (The Pile)

Max Activating Token Index: 599

Text #2

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6854. Min Act: -0.0000

Data Index: 479852 (The Pile)

Max Activating Token Index: 888

Text #3

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.7329. Min Act: -0.0000

Data Index: 1281073 (The Pile)

Max Activating Token Index: 415

Text #4

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6652. Min Act: -0.0000

Data Index: 1795569 (The Pile)

Max Activating Token Index: 534

Text #5

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.7160. Min Act: -0.0000

Data Index: 1549054 (The Pile)

Max Activating Token Index: 643

Text #6

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6695. Min Act: -0.0000

Data Index: 623504 (The Pile)

Max Activating Token Index: 83

Text #7

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6787. Min Act: -0.0000

Data Index: 1924278 (The Pile)

Max Activating Token Index: 283

Text #8

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6309. Min Act: -0.0000

Data Index: 1392887 (The Pile)

Max Activating Token Index: 75

Text #9

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6569. Min Act: -0.0000

Data Index: 89021 (The Pile)

Max Activating Token Index: 910

Text #10

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.5914. Min Act: -0.0000

Data Index: 1919438 (The Pile)

Max Activating Token Index: 493

Text #11

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.5989. Min Act: -0.0000

Data Index: 527219 (The Pile)

Max Activating Token Index: 121

Text #12

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.5990. Min Act: -0.0000

Data Index: 924740 (The Pile)

Max Activating Token Index: 905

Text #13

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.5849. Min Act: -0.0000

Data Index: 959495 (The Pile)

Max Activating Token Index: 18

Text #14

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6034. Min Act: -0.0000

Data Index: 1873302 (The Pile)

Max Activating Token Index: 960

Text #15

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6141. Min Act: -0.0000

Data Index: 634329 (The Pile)

Max Activating Token Index: 157

Text #16

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6136. Min Act: -0.0000

Data Index: 688712 (The Pile)

Max Activating Token Index: 98

Text #17

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6066. Min Act: -0.0000

Data Index: 824951 (The Pile)

Max Activating Token Index: 310

Text #18

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.5804. Min Act: -0.0000

Data Index: 1706482 (The Pile)

Max Activating Token Index: 264

Text #19

Max Range: 0.7758. Min Range: -0.7758

Max Act: 0.6203. Min Act: -0.0000

Data Index: 1593358 (The Pile)

Max Activating Token Index: 606