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

Dataset: The Pile

Neuron 4048 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: 0.5109. Min Range: -0.5109

Max Act: 0.4762. Min Act: -0.0000

Data Index: 1817027 (The Pile)

Max Activating Token Index: 746

Text #1

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.4630. Min Act: -0.0000

Data Index: 557782 (The Pile)

Max Activating Token Index: 873

Text #2

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.4891. Min Act: -0.0000

Data Index: 550796 (The Pile)

Max Activating Token Index: 907

Text #3

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.5109. Min Act: -0.0000

Data Index: 1984908 (The Pile)

Max Activating Token Index: 223

Text #4

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.4422. Min Act: -0.0000

Data Index: 84885 (The Pile)

Max Activating Token Index: 988

Text #5

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3803. Min Act: -0.0000

Data Index: 1451714 (The Pile)

Max Activating Token Index: 826

Text #6

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3536. Min Act: -0.0000

Data Index: 1426291 (The Pile)

Max Activating Token Index: 665

Text #7

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.4324. Min Act: -0.0000

Data Index: 1722246 (The Pile)

Max Activating Token Index: 597

Text #8

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3830. Min Act: -0.0000

Data Index: 1751310 (The Pile)

Max Activating Token Index: 795

Text #9

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.4139. Min Act: -0.0000

Data Index: 1251313 (The Pile)

Max Activating Token Index: 513

Text #10

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.4030. Min Act: -0.0000

Data Index: 400875 (The Pile)

Max Activating Token Index: 219

Text #11

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3653. Min Act: -0.0000

Data Index: 75044 (The Pile)

Max Activating Token Index: 396

Text #12

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.4220. Min Act: -0.0000

Data Index: 1413650 (The Pile)

Max Activating Token Index: 139

Text #13

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3486. Min Act: -0.0000

Data Index: 167143 (The Pile)

Max Activating Token Index: 1013

Text #14

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3458. Min Act: -0.0000

Data Index: 1767472 (The Pile)

Max Activating Token Index: 748

Text #15

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3210. Min Act: -0.0000

Data Index: 653369 (The Pile)

Max Activating Token Index: 345

Text #16

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3168. Min Act: -0.0000

Data Index: 837424 (The Pile)

Max Activating Token Index: 300

Text #17

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.2938. Min Act: -0.0000

Data Index: 680960 (The Pile)

Max Activating Token Index: 799

Text #18

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3237. Min Act: -0.0000

Data Index: 1872456 (The Pile)

Max Activating Token Index: 626

Text #19

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3211. Min Act: -0.0000

Data Index: 402349 (The Pile)

Max Activating Token Index: 395