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

Dataset: The Pile

Neuron 2606 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: 1.4792. Min Range: -1.4792

Max Act: 1.4792. Min Act: -0.0000

Data Index: 1454589 (The Pile)

Max Activating Token Index: 105

Text #1

Max Range: 1.4792. Min Range: -1.4792

Max Act: 1.2725. Min Act: -0.0000

Data Index: 1657997 (The Pile)

Max Activating Token Index: 231

Text #2

Max Range: 1.4792. Min Range: -1.4792

Max Act: 1.3115. Min Act: -0.0000

Data Index: 875668 (The Pile)

Max Activating Token Index: 1009

Text #3

Max Range: 1.4792. Min Range: -1.4792

Max Act: 1.2216. Min Act: -0.0000

Data Index: 647364 (The Pile)

Max Activating Token Index: 843

Text #4

Max Range: 1.4792. Min Range: -1.4792

Max Act: 1.1757. Min Act: -0.0000

Data Index: 855118 (The Pile)

Max Activating Token Index: 1004

Text #5

Max Range: 1.4792. Min Range: -1.4792

Max Act: 1.0528. Min Act: -0.0000

Data Index: 1298883 (The Pile)

Max Activating Token Index: 994

Text #6

Max Range: 1.4792. Min Range: -1.4792

Max Act: 1.0893. Min Act: -0.0000

Data Index: 1549980 (The Pile)

Max Activating Token Index: 901

Text #7

Max Range: 1.4792. Min Range: -1.4792

Max Act: 1.1837. Min Act: -0.0000

Data Index: 68196 (The Pile)

Max Activating Token Index: 982

Text #8

Max Range: 1.4792. Min Range: -1.4792

Max Act: 1.1148. Min Act: -0.0000

Data Index: 368436 (The Pile)

Max Activating Token Index: 974

Text #9

Max Range: 1.4792. Min Range: -1.4792

Max Act: 1.0400. Min Act: -0.0000

Data Index: 898589 (The Pile)

Max Activating Token Index: 424

Text #10

Max Range: 1.4792. Min Range: -1.4792

Max Act: 1.0078. Min Act: -0.0000

Data Index: 828883 (The Pile)

Max Activating Token Index: 986

Text #11

Max Range: 1.4792. Min Range: -1.4792

Max Act: 1.0349. Min Act: -0.0000

Data Index: 1479632 (The Pile)

Max Activating Token Index: 373

Text #12

Max Range: 1.4792. Min Range: -1.4792

Max Act: 1.0365. Min Act: -0.0000

Data Index: 1228093 (The Pile)

Max Activating Token Index: 464

Text #13

Max Range: 1.4792. Min Range: -1.4792

Max Act: 0.9666. Min Act: -0.0000

Data Index: 1616388 (The Pile)

Max Activating Token Index: 603

Text #14

Max Range: 1.4792. Min Range: -1.4792

Max Act: 0.9988. Min Act: -0.0000

Data Index: 1036173 (The Pile)

Max Activating Token Index: 690

Text #15

Max Range: 1.4792. Min Range: -1.4792

Max Act: 1.0530. Min Act: -0.0000

Data Index: 1709007 (The Pile)

Max Activating Token Index: 587

Text #16

Max Range: 1.4792. Min Range: -1.4792

Max Act: 0.9588. Min Act: -0.0000

Data Index: 871049 (The Pile)

Max Activating Token Index: 433

Text #17

Max Range: 1.4792. Min Range: -1.4792

Max Act: 1.0411. Min Act: -0.0000

Data Index: 746705 (The Pile)

Max Activating Token Index: 1007

Text #18

Max Range: 1.4792. Min Range: -1.4792

Max Act: 0.9681. Min Act: -0.0000

Data Index: 1124458 (The Pile)

Max Activating Token Index: 944

Text #19

Max Range: 1.4792. Min Range: -1.4792

Max Act: 1.0696. Min Act: -0.0000

Data Index: 1314666 (The Pile)

Max Activating Token Index: 748