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

Dataset: The Pile

Neuron 960 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3592. Min Range: -1.3592

Max Act: 1.3592. Min Act: -0.0000

Data Index: 716981 (The Pile)

Max Activating Token Index: 755

Text #1

Max Range: 1.3592. Min Range: -1.3592

Max Act: 1.0271. Min Act: -0.0000

Data Index: 150205 (The Pile)

Max Activating Token Index: 764

Text #2

Max Range: 1.3592. Min Range: -1.3592

Max Act: 1.2022. Min Act: -0.0000

Data Index: 946763 (The Pile)

Max Activating Token Index: 177

Text #3

Max Range: 1.3592. Min Range: -1.3592

Max Act: 1.0133. Min Act: -0.0000

Data Index: 846565 (The Pile)

Max Activating Token Index: 638

Text #4

Max Range: 1.3592. Min Range: -1.3592

Max Act: 1.0512. Min Act: -0.0000

Data Index: 511605 (The Pile)

Max Activating Token Index: 167

Text #5

Max Range: 1.3592. Min Range: -1.3592

Max Act: 1.0810. Min Act: -0.0000

Data Index: 1995304 (The Pile)

Max Activating Token Index: 968

Text #6

Max Range: 1.3592. Min Range: -1.3592

Max Act: 1.0880. Min Act: -0.0000

Data Index: 199492 (The Pile)

Max Activating Token Index: 766

Text #7

Max Range: 1.3592. Min Range: -1.3592

Max Act: 1.0599. Min Act: -0.0000

Data Index: 249765 (The Pile)

Max Activating Token Index: 465

Text #8

Max Range: 1.3592. Min Range: -1.3592

Max Act: 1.0074. Min Act: -0.0000

Data Index: 1824402 (The Pile)

Max Activating Token Index: 736

Text #9

Max Range: 1.3592. Min Range: -1.3592

Max Act: 1.0565. Min Act: -0.0000

Data Index: 1374861 (The Pile)

Max Activating Token Index: 1016

Text #10

Max Range: 1.3592. Min Range: -1.3592

Max Act: 0.9711. Min Act: -0.0000

Data Index: 1889576 (The Pile)

Max Activating Token Index: 282

Text #11

Max Range: 1.3592. Min Range: -1.3592

Max Act: 0.9062. Min Act: -0.0000

Data Index: 691029 (The Pile)

Max Activating Token Index: 142

Text #12

Max Range: 1.3592. Min Range: -1.3592

Max Act: 0.9200. Min Act: -0.0000

Data Index: 1884621 (The Pile)

Max Activating Token Index: 681

Text #13

Max Range: 1.3592. Min Range: -1.3592

Max Act: 0.8911. Min Act: -0.0000

Data Index: 582917 (The Pile)

Max Activating Token Index: 788

Text #14

Max Range: 1.3592. Min Range: -1.3592

Max Act: 0.9129. Min Act: -0.0000

Data Index: 123235 (The Pile)

Max Activating Token Index: 578

Text #15

Max Range: 1.3592. Min Range: -1.3592

Max Act: 0.8710. Min Act: -0.0000

Data Index: 1126423 (The Pile)

Max Activating Token Index: 674

Text #16

Max Range: 1.3592. Min Range: -1.3592

Max Act: 0.8970. Min Act: -0.0000

Data Index: 1492076 (The Pile)

Max Activating Token Index: 799

Text #17

Max Range: 1.3592. Min Range: -1.3592

Max Act: 0.8296. Min Act: -0.0000

Data Index: 197987 (The Pile)

Max Activating Token Index: 496

Text #18

Max Range: 1.3592. Min Range: -1.3592

Max Act: 0.8207. Min Act: -0.0000

Data Index: 1013292 (The Pile)

Max Activating Token Index: 172

Text #19

Max Range: 1.3592. Min Range: -1.3592

Max Act: 0.8156. Min Act: -0.0000

Data Index: 1234717 (The Pile)

Max Activating Token Index: 756