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

Dataset: The Pile

Neuron 716 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: 1.5139. Min Range: -1.5139

Max Act: 1.5139. Min Act: -0.0000

Data Index: 1308939 (The Pile)

Max Activating Token Index: 29

Text #1

Max Range: 1.5139. Min Range: -1.5139

Max Act: 1.4193. Min Act: -0.0000

Data Index: 787970 (The Pile)

Max Activating Token Index: 13

Text #2

Max Range: 1.5139. Min Range: -1.5139

Max Act: 1.4668. Min Act: -0.0000

Data Index: 1223974 (The Pile)

Max Activating Token Index: 1021

Text #3

Max Range: 1.5139. Min Range: -1.5139

Max Act: 1.4650. Min Act: -0.0000

Data Index: 105073 (The Pile)

Max Activating Token Index: 1002

Text #4

Max Range: 1.5139. Min Range: -1.5139

Max Act: 1.4329. Min Act: -0.0000

Data Index: 1128624 (The Pile)

Max Activating Token Index: 12

Text #5

Max Range: 1.5139. Min Range: -1.5139

Max Act: 1.4277. Min Act: -0.0000

Data Index: 535371 (The Pile)

Max Activating Token Index: 664

Text #6

Max Range: 1.5139. Min Range: -1.5139

Max Act: 1.4106. Min Act: -0.0000

Data Index: 1976514 (The Pile)

Max Activating Token Index: 454

Text #7

Max Range: 1.5139. Min Range: -1.5139

Max Act: 1.3335. Min Act: -0.0000

Data Index: 1131034 (The Pile)

Max Activating Token Index: 742

Text #8

Max Range: 1.5139. Min Range: -1.5139

Max Act: 1.3814. Min Act: -0.0000

Data Index: 796365 (The Pile)

Max Activating Token Index: 1000

Text #9

Max Range: 1.5139. Min Range: -1.5139

Max Act: 1.3923. Min Act: -0.0000

Data Index: 471329 (The Pile)

Max Activating Token Index: 586

Text #10

Max Range: 1.5139. Min Range: -1.5139

Max Act: 1.3847. Min Act: -0.0000

Data Index: 776374 (The Pile)

Max Activating Token Index: 134

Text #11

Max Range: 1.5139. Min Range: -1.5139

Max Act: 1.4649. Min Act: -0.0000

Data Index: 996953 (The Pile)

Max Activating Token Index: 513

Text #12

Max Range: 1.5139. Min Range: -1.5139

Max Act: 1.3835. Min Act: -0.0000

Data Index: 1321021 (The Pile)

Max Activating Token Index: 236

Text #13

Max Range: 1.5139. Min Range: -1.5139

Max Act: 1.4680. Min Act: -0.0000

Data Index: 1516253 (The Pile)

Max Activating Token Index: 8

Text #14

Max Range: 1.5139. Min Range: -1.5139

Max Act: 1.3802. Min Act: -0.0000

Data Index: 1531329 (The Pile)

Max Activating Token Index: 967

Text #15

Max Range: 1.5139. Min Range: -1.5139

Max Act: 1.3824. Min Act: -0.0000

Data Index: 1028764 (The Pile)

Max Activating Token Index: 592

Text #16

Max Range: 1.5139. Min Range: -1.5139

Max Act: 1.3716. Min Act: -0.0000

Data Index: 1001069 (The Pile)

Max Activating Token Index: 85

Text #17

Max Range: 1.5139. Min Range: -1.5139

Max Act: 1.3629. Min Act: -0.0000

Data Index: 838122 (The Pile)

Max Activating Token Index: 205

Text #18

Max Range: 1.5139. Min Range: -1.5139

Max Act: 1.4265. Min Act: -0.0000

Data Index: 995275 (The Pile)

Max Activating Token Index: 644

Text #19

Max Range: 1.5139. Min Range: -1.5139

Max Act: 1.2684. Min Act: -0.0000

Data Index: 1648795 (The Pile)

Max Activating Token Index: 910