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

Dataset: The Pile

Neuron 1664 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: 0.5686. Min Range: -0.5686

Max Act: 0.5250. Min Act: -0.0000

Data Index: 645635 (The Pile)

Max Activating Token Index: 19

Text #1

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.5030. Min Act: -0.0000

Data Index: 431662 (The Pile)

Max Activating Token Index: 538

Text #2

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.4877. Min Act: -0.0000

Data Index: 1039868 (The Pile)

Max Activating Token Index: 555

Text #3

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.5115. Min Act: -0.0000

Data Index: 202446 (The Pile)

Max Activating Token Index: 756

Text #4

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.5032. Min Act: -0.0000

Data Index: 555596 (The Pile)

Max Activating Token Index: 592

Text #5

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.4947. Min Act: -0.0000

Data Index: 1383735 (The Pile)

Max Activating Token Index: 487

Text #6

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.5251. Min Act: -0.0000

Data Index: 1217395 (The Pile)

Max Activating Token Index: 535

Text #7

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.5150. Min Act: -0.0000

Data Index: 1346092 (The Pile)

Max Activating Token Index: 587

Text #8

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.5160. Min Act: -0.0000

Data Index: 729862 (The Pile)

Max Activating Token Index: 478

Text #9

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.5167. Min Act: -0.0000

Data Index: 1476905 (The Pile)

Max Activating Token Index: 577

Text #10

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.5686. Min Act: -0.0000

Data Index: 1290848 (The Pile)

Max Activating Token Index: 708

Text #11

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.4777. Min Act: -0.0000

Data Index: 161607 (The Pile)

Max Activating Token Index: 864

Text #12

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.5134. Min Act: -0.0000

Data Index: 1645214 (The Pile)

Max Activating Token Index: 601

Text #13

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.5094. Min Act: -0.0000

Data Index: 1098384 (The Pile)

Max Activating Token Index: 536

Text #14

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.5433. Min Act: -0.0000

Data Index: 1354834 (The Pile)

Max Activating Token Index: 588

Text #15

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.4258. Min Act: -0.0000

Data Index: 1042268 (The Pile)

Max Activating Token Index: 670

Text #16

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.4962. Min Act: -0.0000

Data Index: 1638096 (The Pile)

Max Activating Token Index: 793

Text #17

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.5171. Min Act: -0.0000

Data Index: 1477791 (The Pile)

Max Activating Token Index: 730

Text #18

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.4915. Min Act: -0.0000

Data Index: 371767 (The Pile)

Max Activating Token Index: 468

Text #19

Max Range: 0.5686. Min Range: -0.5686

Max Act: 0.5066. Min Act: -0.0000

Data Index: 1720603 (The Pile)

Max Activating Token Index: 625