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

Dataset: The Pile

Neuron 3643 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: 0.9118. Min Range: -0.9118

Max Act: 0.9118. Min Act: -0.0000

Data Index: 1567977 (The Pile)

Max Activating Token Index: 927

Text #1

Max Range: 0.9118. Min Range: -0.9118

Max Act: 0.7533. Min Act: -0.0000

Data Index: 1045137 (The Pile)

Max Activating Token Index: 794

Text #2

Max Range: 0.9118. Min Range: -0.9118

Max Act: 0.6615. Min Act: -0.0000

Data Index: 1424434 (The Pile)

Max Activating Token Index: 1022

Text #3

Max Range: 0.9118. Min Range: -0.9118

Max Act: 0.6249. Min Act: -0.0000

Data Index: 1715900 (The Pile)

Max Activating Token Index: 489

Text #4

Max Range: 0.9118. Min Range: -0.9118

Max Act: 0.6259. Min Act: -0.0000

Data Index: 1554854 (The Pile)

Max Activating Token Index: 32

Text #5

Max Range: 0.9118. Min Range: -0.9118

Max Act: 0.6188. Min Act: -0.0000

Data Index: 1688654 (The Pile)

Max Activating Token Index: 594

Text #6

Max Range: 0.9118. Min Range: -0.9118

Max Act: 0.6194. Min Act: -0.0000

Data Index: 1078259 (The Pile)

Max Activating Token Index: 539

Text #7

Max Range: 0.9118. Min Range: -0.9118

Max Act: 0.5560. Min Act: -0.0000

Data Index: 442564 (The Pile)

Max Activating Token Index: 774

Text #8

Max Range: 0.9118. Min Range: -0.9118

Max Act: 0.5712. Min Act: -0.0000

Data Index: 1158009 (The Pile)

Max Activating Token Index: 294

Text #9

Max Range: 0.9118. Min Range: -0.9118

Max Act: 0.5621. Min Act: -0.0000

Data Index: 688473 (The Pile)

Max Activating Token Index: 935

Text #10

Max Range: 0.9118. Min Range: -0.9118

Max Act: 0.5879. Min Act: -0.0000

Data Index: 271653 (The Pile)

Max Activating Token Index: 463

Text #11

Max Range: 0.9118. Min Range: -0.9118

Max Act: 0.5886. Min Act: -0.0000

Data Index: 1503474 (The Pile)

Max Activating Token Index: 779

Text #12

Max Range: 0.9118. Min Range: -0.9118

Max Act: 0.6011. Min Act: -0.0000

Data Index: 1856526 (The Pile)

Max Activating Token Index: 929

Text #13

Max Range: 0.9118. Min Range: -0.9118

Max Act: 0.5874. Min Act: -0.0000

Data Index: 776163 (The Pile)

Max Activating Token Index: 977

Text #14

Max Range: 0.9118. Min Range: -0.9118

Max Act: 0.5612. Min Act: -0.0000

Data Index: 1838510 (The Pile)

Max Activating Token Index: 355

Text #15

Max Range: 0.9118. Min Range: -0.9118

Max Act: 0.5583. Min Act: -0.0000

Data Index: 1575441 (The Pile)

Max Activating Token Index: 165

Text #16

Max Range: 0.9118. Min Range: -0.9118

Max Act: 0.5557. Min Act: -0.0000

Data Index: 1957287 (The Pile)

Max Activating Token Index: 843

Text #17

Max Range: 0.9118. Min Range: -0.9118

Max Act: 0.5136. Min Act: -0.0000

Data Index: 111737 (The Pile)

Max Activating Token Index: 693

Text #18

Max Range: 0.9118. Min Range: -0.9118

Max Act: 0.5396. Min Act: -0.0000

Data Index: 802351 (The Pile)

Max Activating Token Index: 601

Text #19

Max Range: 0.9118. Min Range: -0.9118

Max Act: 0.5117. Min Act: -0.0000

Data Index: 1672096 (The Pile)

Max Activating Token Index: 837