Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1972 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3936. Min Range: -1.3936

Max Act: 1.3936. Min Act: -0.0000

Data Index: 1411793 (The Pile)

Max Activating Token Index: 406

Text #1

Max Range: 1.3936. Min Range: -1.3936

Max Act: 1.2741. Min Act: -0.0000

Data Index: 863876 (The Pile)

Max Activating Token Index: 140

Text #2

Max Range: 1.3936. Min Range: -1.3936

Max Act: 1.2157. Min Act: -0.0000

Data Index: 204663 (The Pile)

Max Activating Token Index: 242

Text #3

Max Range: 1.3936. Min Range: -1.3936

Max Act: 1.3572. Min Act: -0.0000

Data Index: 1433556 (The Pile)

Max Activating Token Index: 424

Text #4

Max Range: 1.3936. Min Range: -1.3936

Max Act: 1.2647. Min Act: -0.0000

Data Index: 1263725 (The Pile)

Max Activating Token Index: 165

Text #5

Max Range: 1.3936. Min Range: -1.3936

Max Act: 1.2032. Min Act: -0.0000

Data Index: 1790505 (The Pile)

Max Activating Token Index: 36

Text #6

Max Range: 1.3936. Min Range: -1.3936

Max Act: 1.1375. Min Act: -0.0000

Data Index: 1794068 (The Pile)

Max Activating Token Index: 128

Text #7

Max Range: 1.3936. Min Range: -1.3936

Max Act: 1.0741. Min Act: -0.0000

Data Index: 272315 (The Pile)

Max Activating Token Index: 423

Text #8

Max Range: 1.3936. Min Range: -1.3936

Max Act: 1.0665. Min Act: -0.0000

Data Index: 587263 (The Pile)

Max Activating Token Index: 784

Text #9

Max Range: 1.3936. Min Range: -1.3936

Max Act: 1.0963. Min Act: -0.0000

Data Index: 1640313 (The Pile)

Max Activating Token Index: 530

Text #10

Max Range: 1.3936. Min Range: -1.3936

Max Act: 1.1061. Min Act: -0.0000

Data Index: 1276974 (The Pile)

Max Activating Token Index: 235

Text #11

Max Range: 1.3936. Min Range: -1.3936

Max Act: 1.0096. Min Act: -0.0000

Data Index: 200382 (The Pile)

Max Activating Token Index: 423

Text #12

Max Range: 1.3936. Min Range: -1.3936

Max Act: 1.0357. Min Act: -0.0000

Data Index: 1101979 (The Pile)

Max Activating Token Index: 513

Text #13

Max Range: 1.3936. Min Range: -1.3936

Max Act: 1.0590. Min Act: -0.0000

Data Index: 828782 (The Pile)

Max Activating Token Index: 919

Text #14

Max Range: 1.3936. Min Range: -1.3936

Max Act: 1.0140. Min Act: -0.0000

Data Index: 767918 (The Pile)

Max Activating Token Index: 608

Text #15

Max Range: 1.3936. Min Range: -1.3936

Max Act: 1.0093. Min Act: -0.0000

Data Index: 1531979 (The Pile)

Max Activating Token Index: 1008

Text #16

Max Range: 1.3936. Min Range: -1.3936

Max Act: 1.0187. Min Act: -0.0000

Data Index: 1946339 (The Pile)

Max Activating Token Index: 495

Text #17

Max Range: 1.3936. Min Range: -1.3936

Max Act: 0.9779. Min Act: -0.0000

Data Index: 205536 (The Pile)

Max Activating Token Index: 616

Text #18

Max Range: 1.3936. Min Range: -1.3936

Max Act: 0.9732. Min Act: -0.0000

Data Index: 1333752 (The Pile)

Max Activating Token Index: 701

Text #19

Max Range: 1.3936. Min Range: -1.3936

Max Act: 0.9419. Min Act: -0.0000

Data Index: 204383 (The Pile)

Max Activating Token Index: 340