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

Dataset: The Pile

Neuron 3784 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.6436. Min Act: -0.0000

Data Index: 1619393 (The Pile)

Max Activating Token Index: 506

Text #1

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5853. Min Act: -0.0000

Data Index: 1075091 (The Pile)

Max Activating Token Index: 848

Text #2

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.6085. Min Act: -0.0000

Data Index: 632485 (The Pile)

Max Activating Token Index: 336

Text #3

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5526. Min Act: -0.0000

Data Index: 1922566 (The Pile)

Max Activating Token Index: 54

Text #4

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5632. Min Act: -0.0000

Data Index: 325865 (The Pile)

Max Activating Token Index: 230

Text #5

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5362. Min Act: -0.0000

Data Index: 1130413 (The Pile)

Max Activating Token Index: 156

Text #6

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5689. Min Act: -0.0000

Data Index: 728991 (The Pile)

Max Activating Token Index: 246

Text #7

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5622. Min Act: -0.0000

Data Index: 1301870 (The Pile)

Max Activating Token Index: 678

Text #8

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5418. Min Act: -0.0000

Data Index: 1151241 (The Pile)

Max Activating Token Index: 130

Text #9

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5156. Min Act: -0.0000

Data Index: 1954180 (The Pile)

Max Activating Token Index: 825

Text #10

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5036. Min Act: -0.0000

Data Index: 1123325 (The Pile)

Max Activating Token Index: 810

Text #11

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5010. Min Act: -0.0000

Data Index: 549859 (The Pile)

Max Activating Token Index: 133

Text #12

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5351. Min Act: -0.0000

Data Index: 901640 (The Pile)

Max Activating Token Index: 321

Text #13

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5128. Min Act: -0.0000

Data Index: 1784634 (The Pile)

Max Activating Token Index: 964

Text #14

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5136. Min Act: -0.0000

Data Index: 894476 (The Pile)

Max Activating Token Index: 420

Text #15

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.4611. Min Act: -0.0000

Data Index: 1304966 (The Pile)

Max Activating Token Index: 928

Text #16

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.4807. Min Act: -0.0000

Data Index: 1697562 (The Pile)

Max Activating Token Index: 104

Text #17

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.4949. Min Act: -0.0000

Data Index: 220988 (The Pile)

Max Activating Token Index: 664

Text #18

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.4926. Min Act: -0.0000

Data Index: 1546536 (The Pile)

Max Activating Token Index: 969

Text #19

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.4727. Min Act: -0.0000

Data Index: 766409 (The Pile)

Max Activating Token Index: 499