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

Dataset: The Pile

Neuron 4672 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: 0.7232. Min Range: -0.7232

Max Act: 0.7232. Min Act: -0.0000

Data Index: 1426863 (The Pile)

Max Activating Token Index: 368

Text #1

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.6998. Min Act: -0.0000

Data Index: 1401478 (The Pile)

Max Activating Token Index: 149

Text #2

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.6993. Min Act: -0.0000

Data Index: 740784 (The Pile)

Max Activating Token Index: 818

Text #3

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.6560. Min Act: -0.0000

Data Index: 700588 (The Pile)

Max Activating Token Index: 580

Text #4

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.6354. Min Act: -0.0000

Data Index: 1567696 (The Pile)

Max Activating Token Index: 20

Text #5

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.6105. Min Act: -0.0000

Data Index: 1891972 (The Pile)

Max Activating Token Index: 165

Text #6

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.5565. Min Act: -0.0000

Data Index: 1972611 (The Pile)

Max Activating Token Index: 645

Text #7

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.5742. Min Act: -0.0000

Data Index: 556064 (The Pile)

Max Activating Token Index: 808

Text #8

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.5819. Min Act: -0.0000

Data Index: 1176430 (The Pile)

Max Activating Token Index: 106

Text #9

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.5702. Min Act: -0.0000

Data Index: 655040 (The Pile)

Max Activating Token Index: 939

Text #10

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.5232. Min Act: -0.0000

Data Index: 619393 (The Pile)

Max Activating Token Index: 260

Text #11

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.5220. Min Act: -0.0000

Data Index: 1325248 (The Pile)

Max Activating Token Index: 568

Text #12

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.5339. Min Act: -0.0000

Data Index: 901395 (The Pile)

Max Activating Token Index: 951

Text #13

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.5311. Min Act: -0.0000

Data Index: 399922 (The Pile)

Max Activating Token Index: 864

Text #14

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.5407. Min Act: -0.0000

Data Index: 7599 (The Pile)

Max Activating Token Index: 79

Text #15

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.5692. Min Act: -0.0000

Data Index: 188755 (The Pile)

Max Activating Token Index: 692

Text #16

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.5063. Min Act: -0.0000

Data Index: 98659 (The Pile)

Max Activating Token Index: 46

Text #17

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.4857. Min Act: -0.0000

Data Index: 1855245 (The Pile)

Max Activating Token Index: 989

Text #18

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.5158. Min Act: -0.0000

Data Index: 553234 (The Pile)

Max Activating Token Index: 981

Text #19

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.4793. Min Act: -0.0000

Data Index: 1307052 (The Pile)

Max Activating Token Index: 467