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

Dataset: The Pile

Neuron 923 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6239. Min Range: -3.6239

Max Act: 3.6239. Min Act: -0.0000

Data Index: 1630508 (The Pile)

Max Activating Token Index: 822

Text #1

Max Range: 3.6239. Min Range: -3.6239

Max Act: 3.2007. Min Act: -0.0000

Data Index: 1399241 (The Pile)

Max Activating Token Index: 89

Text #2

Max Range: 3.6239. Min Range: -3.6239

Max Act: 3.2752. Min Act: -0.0000

Data Index: 1431781 (The Pile)

Max Activating Token Index: 312

Text #3

Max Range: 3.6239. Min Range: -3.6239

Max Act: 2.9722. Min Act: -0.0000

Data Index: 1167151 (The Pile)

Max Activating Token Index: 76

Text #4

Max Range: 3.6239. Min Range: -3.6239

Max Act: 3.1162. Min Act: -0.0000

Data Index: 736621 (The Pile)

Max Activating Token Index: 812

Text #5

Max Range: 3.6239. Min Range: -3.6239

Max Act: 3.0942. Min Act: -0.0000

Data Index: 758210 (The Pile)

Max Activating Token Index: 13

Text #6

Max Range: 3.6239. Min Range: -3.6239

Max Act: 3.0503. Min Act: -0.0000

Data Index: 1461089 (The Pile)

Max Activating Token Index: 89

Text #7

Max Range: 3.6239. Min Range: -3.6239

Max Act: 3.0525. Min Act: -0.0000

Data Index: 1714309 (The Pile)

Max Activating Token Index: 257

Text #8

Max Range: 3.6239. Min Range: -3.6239

Max Act: 3.0435. Min Act: -0.0000

Data Index: 1535870 (The Pile)

Max Activating Token Index: 724

Text #9

Max Range: 3.6239. Min Range: -3.6239

Max Act: 3.0152. Min Act: -0.0000

Data Index: 1574514 (The Pile)

Max Activating Token Index: 325

Text #10

Max Range: 3.6239. Min Range: -3.6239

Max Act: 2.9840. Min Act: -0.0000

Data Index: 605441 (The Pile)

Max Activating Token Index: 436

Text #11

Max Range: 3.6239. Min Range: -3.6239

Max Act: 2.8217. Min Act: -0.0000

Data Index: 1907755 (The Pile)

Max Activating Token Index: 39

Text #12

Max Range: 3.6239. Min Range: -3.6239

Max Act: 3.0859. Min Act: -0.0000

Data Index: 1868444 (The Pile)

Max Activating Token Index: 101

Text #13

Max Range: 3.6239. Min Range: -3.6239

Max Act: 2.7943. Min Act: -0.0000

Data Index: 1554497 (The Pile)

Max Activating Token Index: 817

Text #14

Max Range: 3.6239. Min Range: -3.6239

Max Act: 2.7725. Min Act: -0.0000

Data Index: 1344064 (The Pile)

Max Activating Token Index: 371

Text #15

Max Range: 3.6239. Min Range: -3.6239

Max Act: 2.8757. Min Act: -0.0000

Data Index: 663311 (The Pile)

Max Activating Token Index: 708

Text #16

Max Range: 3.6239. Min Range: -3.6239

Max Act: 2.8741. Min Act: -0.0000

Data Index: 710612 (The Pile)

Max Activating Token Index: 23

Text #17

Max Range: 3.6239. Min Range: -3.6239

Max Act: 2.8668. Min Act: -0.0000

Data Index: 1165783 (The Pile)

Max Activating Token Index: 114

Text #18

Max Range: 3.6239. Min Range: -3.6239

Max Act: 3.0093. Min Act: -0.0000

Data Index: 1858559 (The Pile)

Max Activating Token Index: 327

Text #19

Max Range: 3.6239. Min Range: -3.6239

Max Act: 2.8301. Min Act: -0.0000

Data Index: 254693 (The Pile)

Max Activating Token Index: 563