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

Dataset: The Pile

Neuron 1445 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4239. Min Range: -1.4239

Max Act: 1.4239. Min Act: -0.0000

Data Index: 1450125 (The Pile)

Max Activating Token Index: 588

Text #1

Max Range: 1.4239. Min Range: -1.4239

Max Act: 1.2679. Min Act: -0.0000

Data Index: 1126473 (The Pile)

Max Activating Token Index: 988

Text #2

Max Range: 1.4239. Min Range: -1.4239

Max Act: 1.2725. Min Act: -0.0000

Data Index: 1499421 (The Pile)

Max Activating Token Index: 886

Text #3

Max Range: 1.4239. Min Range: -1.4239

Max Act: 1.2229. Min Act: -0.0000

Data Index: 1443260 (The Pile)

Max Activating Token Index: 532

Text #4

Max Range: 1.4239. Min Range: -1.4239

Max Act: 1.2498. Min Act: -0.0000

Data Index: 375677 (The Pile)

Max Activating Token Index: 892

Text #5

Max Range: 1.4239. Min Range: -1.4239

Max Act: 1.0826. Min Act: -0.0000

Data Index: 512186 (The Pile)

Max Activating Token Index: 29

Text #6

Max Range: 1.4239. Min Range: -1.4239

Max Act: 1.2073. Min Act: -0.0000

Data Index: 716719 (The Pile)

Max Activating Token Index: 10

Text #7

Max Range: 1.4239. Min Range: -1.4239

Max Act: 1.0974. Min Act: -0.0000

Data Index: 1704517 (The Pile)

Max Activating Token Index: 941

Text #8

Max Range: 1.4239. Min Range: -1.4239

Max Act: 1.1740. Min Act: -0.0000

Data Index: 1402340 (The Pile)

Max Activating Token Index: 603

Text #9

Max Range: 1.4239. Min Range: -1.4239

Max Act: 1.1583. Min Act: -0.0000

Data Index: 709495 (The Pile)

Max Activating Token Index: 88

Text #10

Max Range: 1.4239. Min Range: -1.4239

Max Act: 1.1077. Min Act: -0.0000

Data Index: 979653 (The Pile)

Max Activating Token Index: 502

Text #11

Max Range: 1.4239. Min Range: -1.4239

Max Act: 1.0430. Min Act: -0.0000

Data Index: 375165 (The Pile)

Max Activating Token Index: 560

Text #12

Max Range: 1.4239. Min Range: -1.4239

Max Act: 1.0696. Min Act: -0.0000

Data Index: 1354586 (The Pile)

Max Activating Token Index: 809

Text #13

Max Range: 1.4239. Min Range: -1.4239

Max Act: 1.0260. Min Act: -0.0000

Data Index: 760396 (The Pile)

Max Activating Token Index: 31

Text #14

Max Range: 1.4239. Min Range: -1.4239

Max Act: 1.0083. Min Act: -0.0000

Data Index: 821387 (The Pile)

Max Activating Token Index: 186

Text #15

Max Range: 1.4239. Min Range: -1.4239

Max Act: 1.0084. Min Act: -0.0000

Data Index: 13508 (The Pile)

Max Activating Token Index: 355

Text #16

Max Range: 1.4239. Min Range: -1.4239

Max Act: 0.9779. Min Act: -0.0000

Data Index: 569040 (The Pile)

Max Activating Token Index: 350

Text #17

Max Range: 1.4239. Min Range: -1.4239

Max Act: 0.9940. Min Act: -0.0000

Data Index: 1229970 (The Pile)

Max Activating Token Index: 205

Text #18

Max Range: 1.4239. Min Range: -1.4239

Max Act: 0.9732. Min Act: -0.0000

Data Index: 687203 (The Pile)

Max Activating Token Index: 993

Text #19

Max Range: 1.4239. Min Range: -1.4239

Max Act: 0.9937. Min Act: -0.0000

Data Index: 887468 (The Pile)

Max Activating Token Index: 177