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

Dataset: The Pile

Neuron 4374 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: 1.9220. Min Range: -1.9220

Max Act: 1.9220. Min Act: -0.0000

Data Index: 490926 (The Pile)

Max Activating Token Index: 344

Text #1

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.7151. Min Act: -0.0000

Data Index: 138927 (The Pile)

Max Activating Token Index: 121

Text #2

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.5710. Min Act: -0.0000

Data Index: 1446134 (The Pile)

Max Activating Token Index: 522

Text #3

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.5251. Min Act: -0.0000

Data Index: 100607 (The Pile)

Max Activating Token Index: 53

Text #4

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.4903. Min Act: -0.0000

Data Index: 1693467 (The Pile)

Max Activating Token Index: 230

Text #5

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.4868. Min Act: -0.0000

Data Index: 1581919 (The Pile)

Max Activating Token Index: 472

Text #6

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.4772. Min Act: -0.0000

Data Index: 687685 (The Pile)

Max Activating Token Index: 710

Text #7

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.4668. Min Act: -0.0000

Data Index: 1150977 (The Pile)

Max Activating Token Index: 382

Text #8

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.4592. Min Act: -0.0000

Data Index: 1362290 (The Pile)

Max Activating Token Index: 90

Text #9

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.4527. Min Act: -0.0000

Data Index: 729413 (The Pile)

Max Activating Token Index: 50

Text #10

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.4153. Min Act: -0.0000

Data Index: 1353717 (The Pile)

Max Activating Token Index: 898

Text #11

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.2534. Min Act: -0.0000

Data Index: 1590850 (The Pile)

Max Activating Token Index: 27

Text #12

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.2463. Min Act: -0.0000

Data Index: 200733 (The Pile)

Max Activating Token Index: 221

Text #13

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.1295. Min Act: -0.0000

Data Index: 1165230 (The Pile)

Max Activating Token Index: 65

Text #14

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.1852. Min Act: -0.0000

Data Index: 90654 (The Pile)

Max Activating Token Index: 980

Text #15

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.0404. Min Act: -0.0000

Data Index: 1752331 (The Pile)

Max Activating Token Index: 53

Text #16

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.1877. Min Act: -0.0000

Data Index: 1306157 (The Pile)

Max Activating Token Index: 107

Text #17

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.1027. Min Act: -0.0000

Data Index: 975368 (The Pile)

Max Activating Token Index: 98

Text #18

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.1657. Min Act: -0.0000

Data Index: 1230311 (The Pile)

Max Activating Token Index: 370

Text #19

Max Range: 1.9220. Min Range: -1.9220

Max Act: 1.0972. Min Act: -0.0000

Data Index: 1267184 (The Pile)

Max Activating Token Index: 53