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

Dataset: The Pile

Neuron 3347 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: 1.1065. Min Range: -1.1065

Max Act: 1.0135. Min Act: -0.0000

Data Index: 1890324 (The Pile)

Max Activating Token Index: 643

Text #1

Max Range: 1.1065. Min Range: -1.1065

Max Act: 1.1065. Min Act: -0.0000

Data Index: 65808 (The Pile)

Max Activating Token Index: 860

Text #2

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.9810. Min Act: -0.0000

Data Index: 989203 (The Pile)

Max Activating Token Index: 738

Text #3

Max Range: 1.1065. Min Range: -1.1065

Max Act: 1.0669. Min Act: -0.0000

Data Index: 213310 (The Pile)

Max Activating Token Index: 268

Text #4

Max Range: 1.1065. Min Range: -1.1065

Max Act: 1.0043. Min Act: -0.0000

Data Index: 1101693 (The Pile)

Max Activating Token Index: 775

Text #5

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.9677. Min Act: -0.0000

Data Index: 1463663 (The Pile)

Max Activating Token Index: 561

Text #6

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.8419. Min Act: -0.0000

Data Index: 427622 (The Pile)

Max Activating Token Index: 49

Text #7

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.8984. Min Act: -0.0000

Data Index: 1916234 (The Pile)

Max Activating Token Index: 96

Text #8

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.8533. Min Act: -0.0000

Data Index: 719159 (The Pile)

Max Activating Token Index: 614

Text #9

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.8348. Min Act: -0.0000

Data Index: 1232883 (The Pile)

Max Activating Token Index: 354

Text #10

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.8225. Min Act: -0.0000

Data Index: 1920171 (The Pile)

Max Activating Token Index: 295

Text #11

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.7683. Min Act: -0.0000

Data Index: 1587912 (The Pile)

Max Activating Token Index: 177

Text #12

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.7828. Min Act: -0.0000

Data Index: 16313 (The Pile)

Max Activating Token Index: 35

Text #13

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.7775. Min Act: -0.0000

Data Index: 856852 (The Pile)

Max Activating Token Index: 104

Text #14

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.7516. Min Act: -0.0000

Data Index: 1958615 (The Pile)

Max Activating Token Index: 966

Text #15

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.7652. Min Act: -0.0000

Data Index: 624743 (The Pile)

Max Activating Token Index: 283

Text #16

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.7322. Min Act: -0.0000

Data Index: 155280 (The Pile)

Max Activating Token Index: 855

Text #17

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.6884. Min Act: -0.0000

Data Index: 628089 (The Pile)

Max Activating Token Index: 814

Text #18

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.7750. Min Act: -0.0000

Data Index: 1032689 (The Pile)

Max Activating Token Index: 548

Text #19

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.7692. Min Act: -0.0000

Data Index: 1265653 (The Pile)

Max Activating Token Index: 142