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

Dataset: The Pile

Neuron 229 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: 0.7135. Min Range: -0.7135

Max Act: 0.6821. Min Act: -0.0000

Data Index: 1640610 (The Pile)

Max Activating Token Index: 627

Text #1

Max Range: 0.7135. Min Range: -0.7135

Max Act: 0.7135. Min Act: -0.0000

Data Index: 1996858 (The Pile)

Max Activating Token Index: 1003

Text #2

Max Range: 0.7135. Min Range: -0.7135

Max Act: 0.6528. Min Act: -0.0000

Data Index: 1783912 (The Pile)

Max Activating Token Index: 379

Text #3

Max Range: 0.7135. Min Range: -0.7135

Max Act: 0.5992. Min Act: -0.0000

Data Index: 755893 (The Pile)

Max Activating Token Index: 469

Text #4

Max Range: 0.7135. Min Range: -0.7135

Max Act: 0.5988. Min Act: -0.0000

Data Index: 1805021 (The Pile)

Max Activating Token Index: 484

Text #5

Max Range: 0.7135. Min Range: -0.7135

Max Act: 0.5610. Min Act: -0.0000

Data Index: 247856 (The Pile)

Max Activating Token Index: 538

Text #6

Max Range: 0.7135. Min Range: -0.7135

Max Act: 0.5288. Min Act: -0.0000

Data Index: 168647 (The Pile)

Max Activating Token Index: 893

Text #7

Max Range: 0.7135. Min Range: -0.7135

Max Act: 0.5262. Min Act: -0.0000

Data Index: 425649 (The Pile)

Max Activating Token Index: 569

Text #8

Max Range: 0.7135. Min Range: -0.7135

Max Act: 0.5509. Min Act: -0.0000

Data Index: 1779025 (The Pile)

Max Activating Token Index: 87

Text #9

Max Range: 0.7135. Min Range: -0.7135

Max Act: 0.5355. Min Act: -0.0000

Data Index: 1951998 (The Pile)

Max Activating Token Index: 680

Text #10

Max Range: 0.7135. Min Range: -0.7135

Max Act: 0.5459. Min Act: -0.0000

Data Index: 1676490 (The Pile)

Max Activating Token Index: 741

Text #11

Max Range: 0.7135. Min Range: -0.7135

Max Act: 0.5080. Min Act: -0.0000

Data Index: 290603 (The Pile)

Max Activating Token Index: 479

Text #12

Max Range: 0.7135. Min Range: -0.7135

Max Act: 0.5267. Min Act: -0.0000

Data Index: 1902233 (The Pile)

Max Activating Token Index: 994

Text #13

Max Range: 0.7135. Min Range: -0.7135

Max Act: 0.5259. Min Act: -0.0000

Data Index: 751623 (The Pile)

Max Activating Token Index: 136

Text #14

Max Range: 0.7135. Min Range: -0.7135

Max Act: 0.4935. Min Act: -0.0000

Data Index: 1703736 (The Pile)

Max Activating Token Index: 825

Text #15

Max Range: 0.7135. Min Range: -0.7135

Max Act: 0.4374. Min Act: -0.0000

Data Index: 946728 (The Pile)

Max Activating Token Index: 734

Text #16

Max Range: 0.7135. Min Range: -0.7135

Max Act: 0.4958. Min Act: -0.0000

Data Index: 450713 (The Pile)

Max Activating Token Index: 210

Text #17

Max Range: 0.7135. Min Range: -0.7135

Max Act: 0.5049. Min Act: -0.0000

Data Index: 1779897 (The Pile)

Max Activating Token Index: 985

Text #18

Max Range: 0.7135. Min Range: -0.7135

Max Act: 0.4639. Min Act: -0.0000

Data Index: 748510 (The Pile)

Max Activating Token Index: 371

Text #19

Max Range: 0.7135. Min Range: -0.7135

Max Act: 0.4698. Min Act: -0.0000

Data Index: 588314 (The Pile)

Max Activating Token Index: 560