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

Dataset: The Pile

Neuron 3370 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: 5.2662. Min Range: -5.2662

Max Act: 5.2662. Min Act: -0.0000

Data Index: 1440319 (The Pile)

Max Activating Token Index: 638

Text #1

Max Range: 5.2662. Min Range: -5.2662

Max Act: 4.7833. Min Act: -0.0000

Data Index: 1305722 (The Pile)

Max Activating Token Index: 818

Text #2

Max Range: 5.2662. Min Range: -5.2662

Max Act: 4.3528. Min Act: -0.0000

Data Index: 1773912 (The Pile)

Max Activating Token Index: 1009

Text #3

Max Range: 5.2662. Min Range: -5.2662

Max Act: 4.7124. Min Act: -0.0000

Data Index: 1851011 (The Pile)

Max Activating Token Index: 893

Text #4

Max Range: 5.2662. Min Range: -5.2662

Max Act: 4.0980. Min Act: -0.0000

Data Index: 1729303 (The Pile)

Max Activating Token Index: 509

Text #5

Max Range: 5.2662. Min Range: -5.2662

Max Act: 4.0469. Min Act: -0.0000

Data Index: 963628 (The Pile)

Max Activating Token Index: 527

Text #6

Max Range: 5.2662. Min Range: -5.2662

Max Act: 4.1215. Min Act: -0.0000

Data Index: 508319 (The Pile)

Max Activating Token Index: 1013

Text #7

Max Range: 5.2662. Min Range: -5.2662

Max Act: 4.1378. Min Act: -0.0000

Data Index: 150217 (The Pile)

Max Activating Token Index: 294

Text #8

Max Range: 5.2662. Min Range: -5.2662

Max Act: 3.5755. Min Act: -0.0000

Data Index: 1932728 (The Pile)

Max Activating Token Index: 892

Text #9

Max Range: 5.2662. Min Range: -5.2662

Max Act: 4.1320. Min Act: -0.0000

Data Index: 977238 (The Pile)

Max Activating Token Index: 533

Text #10

Max Range: 5.2662. Min Range: -5.2662

Max Act: 3.7921. Min Act: -0.0000

Data Index: 866448 (The Pile)

Max Activating Token Index: 950

Text #11

Max Range: 5.2662. Min Range: -5.2662

Max Act: 3.1737. Min Act: -0.0000

Data Index: 161821 (The Pile)

Max Activating Token Index: 692

Text #12

Max Range: 5.2662. Min Range: -5.2662

Max Act: 3.3379. Min Act: -0.0000

Data Index: 1296721 (The Pile)

Max Activating Token Index: 872

Text #13

Max Range: 5.2662. Min Range: -5.2662

Max Act: 3.3180. Min Act: -0.0000

Data Index: 382581 (The Pile)

Max Activating Token Index: 677

Text #14

Max Range: 5.2662. Min Range: -5.2662

Max Act: 3.9407. Min Act: -0.0000

Data Index: 1069950 (The Pile)

Max Activating Token Index: 785

Text #15

Max Range: 5.2662. Min Range: -5.2662

Max Act: 3.7099. Min Act: -0.0000

Data Index: 727570 (The Pile)

Max Activating Token Index: 970

Text #16

Max Range: 5.2662. Min Range: -5.2662

Max Act: 3.2919. Min Act: -0.0000

Data Index: 1349121 (The Pile)

Max Activating Token Index: 1018

Text #17

Max Range: 5.2662. Min Range: -5.2662

Max Act: 3.9820. Min Act: -0.0000

Data Index: 881251 (The Pile)

Max Activating Token Index: 1007

Text #18

Max Range: 5.2662. Min Range: -5.2662

Max Act: 3.3891. Min Act: -0.0000

Data Index: 700593 (The Pile)

Max Activating Token Index: 903

Text #19

Max Range: 5.2662. Min Range: -5.2662

Max Act: 3.6294. Min Act: -0.0000

Data Index: 62042 (The Pile)

Max Activating Token Index: 561