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

Dataset: The Pile

Neuron 4625 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.7817. Min Act: -0.0000

Data Index: 832621 (The Pile)

Max Activating Token Index: 964

Text #1

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.6718. Min Act: -0.0000

Data Index: 25598 (The Pile)

Max Activating Token Index: 997

Text #2

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.6319. Min Act: -0.0000

Data Index: 782154 (The Pile)

Max Activating Token Index: 628

Text #3

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.6721. Min Act: -0.0000

Data Index: 32459 (The Pile)

Max Activating Token Index: 363

Text #4

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.5726. Min Act: -0.0000

Data Index: 1399668 (The Pile)

Max Activating Token Index: 533

Text #5

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.5741. Min Act: -0.0000

Data Index: 1875908 (The Pile)

Max Activating Token Index: 227

Text #6

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.5653. Min Act: -0.0000

Data Index: 87235 (The Pile)

Max Activating Token Index: 800

Text #7

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.5865. Min Act: -0.0000

Data Index: 201212 (The Pile)

Max Activating Token Index: 185

Text #8

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.5139. Min Act: -0.0000

Data Index: 1056788 (The Pile)

Max Activating Token Index: 137

Text #9

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.5427. Min Act: -0.0000

Data Index: 1016116 (The Pile)

Max Activating Token Index: 443

Text #10

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.5500. Min Act: -0.0000

Data Index: 1347720 (The Pile)

Max Activating Token Index: 621

Text #11

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.5134. Min Act: -0.0000

Data Index: 1431869 (The Pile)

Max Activating Token Index: 23

Text #12

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.5252. Min Act: -0.0000

Data Index: 1983527 (The Pile)

Max Activating Token Index: 931

Text #13

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.5411. Min Act: -0.0000

Data Index: 1711805 (The Pile)

Max Activating Token Index: 944

Text #14

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.5081. Min Act: -0.0000

Data Index: 235275 (The Pile)

Max Activating Token Index: 275

Text #15

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.5192. Min Act: -0.0000

Data Index: 1148605 (The Pile)

Max Activating Token Index: 943

Text #16

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.5021. Min Act: -0.0000

Data Index: 874866 (The Pile)

Max Activating Token Index: 120

Text #17

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.5141. Min Act: -0.0000

Data Index: 774839 (The Pile)

Max Activating Token Index: 147

Text #18

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.4973. Min Act: -0.0000

Data Index: 1142686 (The Pile)

Max Activating Token Index: 52

Text #19

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.5122. Min Act: -0.0000

Data Index: 671235 (The Pile)

Max Activating Token Index: 589