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

Dataset: The Pile

Neuron 1435 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3735. Min Range: -1.3735

Max Act: 1.3735. Min Act: -0.0000

Data Index: 291675 (The Pile)

Max Activating Token Index: 362

Text #1

Max Range: 1.3735. Min Range: -1.3735

Max Act: 1.2641. Min Act: -0.0000

Data Index: 710755 (The Pile)

Max Activating Token Index: 726

Text #2

Max Range: 1.3735. Min Range: -1.3735

Max Act: 1.1170. Min Act: -0.0000

Data Index: 1327924 (The Pile)

Max Activating Token Index: 716

Text #3

Max Range: 1.3735. Min Range: -1.3735

Max Act: 0.9956. Min Act: -0.0000

Data Index: 1000187 (The Pile)

Max Activating Token Index: 681

Text #4

Max Range: 1.3735. Min Range: -1.3735

Max Act: 0.9777. Min Act: -0.0000

Data Index: 665974 (The Pile)

Max Activating Token Index: 460

Text #5

Max Range: 1.3735. Min Range: -1.3735

Max Act: 1.0555. Min Act: -0.0000

Data Index: 1076592 (The Pile)

Max Activating Token Index: 538

Text #6

Max Range: 1.3735. Min Range: -1.3735

Max Act: 0.9919. Min Act: -0.0000

Data Index: 1124898 (The Pile)

Max Activating Token Index: 736

Text #7

Max Range: 1.3735. Min Range: -1.3735

Max Act: 1.0233. Min Act: -0.0000

Data Index: 424150 (The Pile)

Max Activating Token Index: 132

Text #8

Max Range: 1.3735. Min Range: -1.3735

Max Act: 1.0269. Min Act: -0.0000

Data Index: 629287 (The Pile)

Max Activating Token Index: 360

Text #9

Max Range: 1.3735. Min Range: -1.3735

Max Act: 0.9528. Min Act: -0.0000

Data Index: 1840782 (The Pile)

Max Activating Token Index: 99

Text #10

Max Range: 1.3735. Min Range: -1.3735

Max Act: 0.7560. Min Act: -0.0000

Data Index: 485790 (The Pile)

Max Activating Token Index: 865

Text #11

Max Range: 1.3735. Min Range: -1.3735

Max Act: 0.8472. Min Act: -0.0000

Data Index: 208172 (The Pile)

Max Activating Token Index: 324

Text #12

Max Range: 1.3735. Min Range: -1.3735

Max Act: 0.8828. Min Act: -0.0000

Data Index: 573338 (The Pile)

Max Activating Token Index: 555

Text #13

Max Range: 1.3735. Min Range: -1.3735

Max Act: 0.8187. Min Act: -0.0000

Data Index: 859377 (The Pile)

Max Activating Token Index: 334

Text #14

Max Range: 1.3735. Min Range: -1.3735

Max Act: 0.9844. Min Act: -0.0000

Data Index: 762159 (The Pile)

Max Activating Token Index: 80

Text #15

Max Range: 1.3735. Min Range: -1.3735

Max Act: 0.8265. Min Act: -0.0000

Data Index: 1879528 (The Pile)

Max Activating Token Index: 255

Text #16

Max Range: 1.3735. Min Range: -1.3735

Max Act: 0.7778. Min Act: -0.0000

Data Index: 1862853 (The Pile)

Max Activating Token Index: 767

Text #17

Max Range: 1.3735. Min Range: -1.3735

Max Act: 0.8168. Min Act: -0.0000

Data Index: 253234 (The Pile)

Max Activating Token Index: 307

Text #18

Max Range: 1.3735. Min Range: -1.3735

Max Act: 0.7716. Min Act: -0.0000

Data Index: 869843 (The Pile)

Max Activating Token Index: 528

Text #19

Max Range: 1.3735. Min Range: -1.3735

Max Act: 0.7608. Min Act: -0.0000

Data Index: 1604634 (The Pile)

Max Activating Token Index: 907