Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2407 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.8184. Min Act: -0.0000

Data Index: 1106920 (The Pile)

Max Activating Token Index: 491

Text #1

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.8404. Min Act: -0.0000

Data Index: 1151471 (The Pile)

Max Activating Token Index: 83

Text #2

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.7756. Min Act: -0.0000

Data Index: 1546600 (The Pile)

Max Activating Token Index: 978

Text #3

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.7336. Min Act: -0.0000

Data Index: 1027332 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.6730. Min Act: -0.0000

Data Index: 1041461 (The Pile)

Max Activating Token Index: 937

Text #5

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.6806. Min Act: -0.0000

Data Index: 1338392 (The Pile)

Max Activating Token Index: 61

Text #6

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.7039. Min Act: -0.0000

Data Index: 1726372 (The Pile)

Max Activating Token Index: 975

Text #7

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.7178. Min Act: -0.0000

Data Index: 1997763 (The Pile)

Max Activating Token Index: 239

Text #8

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.6627. Min Act: -0.0000

Data Index: 1547925 (The Pile)

Max Activating Token Index: 393

Text #9

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.6616. Min Act: -0.0000

Data Index: 1844471 (The Pile)

Max Activating Token Index: 481

Text #10

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.6468. Min Act: -0.0000

Data Index: 1940701 (The Pile)

Max Activating Token Index: 636

Text #11

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.6607. Min Act: -0.0000

Data Index: 1218831 (The Pile)

Max Activating Token Index: 6

Text #12

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.6160. Min Act: -0.0000

Data Index: 170318 (The Pile)

Max Activating Token Index: 637

Text #13

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.6530. Min Act: -0.0000

Data Index: 524183 (The Pile)

Max Activating Token Index: 627

Text #14

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.6824. Min Act: -0.0000

Data Index: 1747947 (The Pile)

Max Activating Token Index: 3

Text #15

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.6329. Min Act: -0.0000

Data Index: 1188053 (The Pile)

Max Activating Token Index: 1009

Text #16

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.6789. Min Act: -0.0000

Data Index: 871439 (The Pile)

Max Activating Token Index: 285

Text #17

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.6513. Min Act: -0.0000

Data Index: 983182 (The Pile)

Max Activating Token Index: 69

Text #18

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.6491. Min Act: -0.0000

Data Index: 63565 (The Pile)

Max Activating Token Index: 387

Text #19

Max Range: 0.8404. Min Range: -0.8404

Max Act: 0.6456. Min Act: -0.0000

Data Index: 704791 (The Pile)

Max Activating Token Index: 713