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

Dataset: The Pile

Neuron 3920 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: 1.2109. Min Range: -1.2109

Max Act: 1.2109. Min Act: -0.0000

Data Index: 1842997 (The Pile)

Max Activating Token Index: 1004

Text #1

Max Range: 1.2109. Min Range: -1.2109

Max Act: 1.0999. Min Act: -0.0000

Data Index: 596723 (The Pile)

Max Activating Token Index: 979

Text #2

Max Range: 1.2109. Min Range: -1.2109

Max Act: 1.1900. Min Act: -0.0000

Data Index: 720177 (The Pile)

Max Activating Token Index: 681

Text #3

Max Range: 1.2109. Min Range: -1.2109

Max Act: 1.0423. Min Act: -0.0000

Data Index: 71088 (The Pile)

Max Activating Token Index: 740

Text #4

Max Range: 1.2109. Min Range: -1.2109

Max Act: 1.0193. Min Act: -0.0000

Data Index: 1661631 (The Pile)

Max Activating Token Index: 284

Text #5

Max Range: 1.2109. Min Range: -1.2109

Max Act: 1.0115. Min Act: -0.0000

Data Index: 1162490 (The Pile)

Max Activating Token Index: 537

Text #6

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.9909. Min Act: -0.0000

Data Index: 955238 (The Pile)

Max Activating Token Index: 316

Text #7

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.9911. Min Act: -0.0000

Data Index: 1738273 (The Pile)

Max Activating Token Index: 772

Text #8

Max Range: 1.2109. Min Range: -1.2109

Max Act: 1.0906. Min Act: -0.0000

Data Index: 275275 (The Pile)

Max Activating Token Index: 114

Text #9

Max Range: 1.2109. Min Range: -1.2109

Max Act: 1.0000. Min Act: -0.0000

Data Index: 1431554 (The Pile)

Max Activating Token Index: 496

Text #10

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.9215. Min Act: -0.0000

Data Index: 482297 (The Pile)

Max Activating Token Index: 772

Text #11

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.9942. Min Act: -0.0000

Data Index: 165512 (The Pile)

Max Activating Token Index: 494

Text #12

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.8993. Min Act: -0.0000

Data Index: 1221329 (The Pile)

Max Activating Token Index: 514

Text #13

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.8775. Min Act: -0.0000

Data Index: 1189036 (The Pile)

Max Activating Token Index: 838

Text #14

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.8987. Min Act: -0.0000

Data Index: 177523 (The Pile)

Max Activating Token Index: 273

Text #15

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.9881. Min Act: -0.0000

Data Index: 1798608 (The Pile)

Max Activating Token Index: 467

Text #16

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.9796. Min Act: -0.0000

Data Index: 1012030 (The Pile)

Max Activating Token Index: 965

Text #17

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.9204. Min Act: -0.0000

Data Index: 303699 (The Pile)

Max Activating Token Index: 607

Text #18

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.9552. Min Act: -0.0000

Data Index: 1495722 (The Pile)

Max Activating Token Index: 878

Text #19

Max Range: 1.2109. Min Range: -1.2109

Max Act: 0.9936. Min Act: -0.0000

Data Index: 1373057 (The Pile)

Max Activating Token Index: 192