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

Dataset: The Pile

Neuron 1982 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: 0.8586. Min Range: -0.8586

Max Act: 0.8586. Min Act: -0.0000

Data Index: 128036 (The Pile)

Max Activating Token Index: 769

Text #1

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.4288. Min Act: -0.0000

Data Index: 1212221 (The Pile)

Max Activating Token Index: 401

Text #2

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.3156. Min Act: -0.0000

Data Index: 143687 (The Pile)

Max Activating Token Index: 906

Text #3

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.3538. Min Act: -0.0000

Data Index: 9105 (The Pile)

Max Activating Token Index: 957

Text #4

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.3183. Min Act: -0.0000

Data Index: 986250 (The Pile)

Max Activating Token Index: 938

Text #5

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.2877. Min Act: -0.0000

Data Index: 674470 (The Pile)

Max Activating Token Index: 682

Text #6

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.2660. Min Act: -0.0000

Data Index: 1959543 (The Pile)

Max Activating Token Index: 847

Text #7

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.3198. Min Act: -0.0000

Data Index: 1920655 (The Pile)

Max Activating Token Index: 983

Text #8

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.2905. Min Act: -0.0000

Data Index: 470013 (The Pile)

Max Activating Token Index: 319

Text #9

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.2869. Min Act: -0.0000

Data Index: 1109223 (The Pile)

Max Activating Token Index: 706

Text #10

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.2548. Min Act: -0.0000

Data Index: 1693907 (The Pile)

Max Activating Token Index: 662

Text #11

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.2571. Min Act: -0.0000

Data Index: 1009733 (The Pile)

Max Activating Token Index: 405

Text #12

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.2645. Min Act: -0.0000

Data Index: 1916919 (The Pile)

Max Activating Token Index: 305

Text #13

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.2497. Min Act: -0.0000

Data Index: 1089738 (The Pile)

Max Activating Token Index: 451

Text #14

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.2402. Min Act: -0.0000

Data Index: 991178 (The Pile)

Max Activating Token Index: 809

Text #15

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.2486. Min Act: -0.0000

Data Index: 1738121 (The Pile)

Max Activating Token Index: 968

Text #16

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.2395. Min Act: -0.0000

Data Index: 996387 (The Pile)

Max Activating Token Index: 224

Text #17

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.2349. Min Act: -0.0000

Data Index: 1418728 (The Pile)

Max Activating Token Index: 162

Text #18

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.2438. Min Act: -0.0000

Data Index: 829801 (The Pile)

Max Activating Token Index: 737

Text #19

Max Range: 0.8586. Min Range: -0.8586

Max Act: 0.2360. Min Act: -0.0000

Data Index: 1285629 (The Pile)

Max Activating Token Index: 692