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

Dataset: The Pile

Neuron 3785 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.8760. Min Act: -0.0000

Data Index: 1416859 (The Pile)

Max Activating Token Index: 548

Text #1

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.9786. Min Act: -0.0000

Data Index: 117662 (The Pile)

Max Activating Token Index: 387

Text #2

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.9241. Min Act: -0.0000

Data Index: 1539532 (The Pile)

Max Activating Token Index: 516

Text #3

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.8381. Min Act: -0.0000

Data Index: 857201 (The Pile)

Max Activating Token Index: 380

Text #4

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.6947. Min Act: -0.0000

Data Index: 391876 (The Pile)

Max Activating Token Index: 945

Text #5

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.7689. Min Act: -0.0000

Data Index: 1467176 (The Pile)

Max Activating Token Index: 245

Text #6

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.6439. Min Act: -0.0000

Data Index: 872576 (The Pile)

Max Activating Token Index: 750

Text #7

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.6657. Min Act: -0.0000

Data Index: 1717852 (The Pile)

Max Activating Token Index: 613

Text #8

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.5991. Min Act: -0.0000

Data Index: 1308297 (The Pile)

Max Activating Token Index: 812

Text #9

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.6548. Min Act: -0.0000

Data Index: 1081944 (The Pile)

Max Activating Token Index: 531

Text #10

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.5902. Min Act: -0.0000

Data Index: 790050 (The Pile)

Max Activating Token Index: 275

Text #11

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.5558. Min Act: -0.0000

Data Index: 1981465 (The Pile)

Max Activating Token Index: 947

Text #12

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.5707. Min Act: -0.0000

Data Index: 1899000 (The Pile)

Max Activating Token Index: 878

Text #13

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.5482. Min Act: -0.0000

Data Index: 1929383 (The Pile)

Max Activating Token Index: 304

Text #14

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.5450. Min Act: -0.0000

Data Index: 1936905 (The Pile)

Max Activating Token Index: 915

Text #15

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.5828. Min Act: -0.0000

Data Index: 1988212 (The Pile)

Max Activating Token Index: 869

Text #16

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.4584. Min Act: -0.0000

Data Index: 1733432 (The Pile)

Max Activating Token Index: 632

Text #17

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.5009. Min Act: -0.0000

Data Index: 1258115 (The Pile)

Max Activating Token Index: 495

Text #18

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.5010. Min Act: -0.0000

Data Index: 1332458 (The Pile)

Max Activating Token Index: 597

Text #19

Max Range: 0.9786. Min Range: -0.9786

Max Act: 0.4615. Min Act: -0.0000

Data Index: 1998162 (The Pile)

Max Activating Token Index: 523