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

Dataset: The Pile

Neuron 1501 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5758. Min Range: -0.5758

Max Act: 0.5758. Min Act: -0.0000

Data Index: 1905525 (The Pile)

Max Activating Token Index: 908

Text #1

Max Range: 0.5758. Min Range: -0.5758

Max Act: 0.4804. Min Act: -0.0000

Data Index: 663987 (The Pile)

Max Activating Token Index: 668

Text #2

Max Range: 0.5758. Min Range: -0.5758

Max Act: 0.4880. Min Act: -0.0000

Data Index: 169667 (The Pile)

Max Activating Token Index: 73

Text #3

Max Range: 0.5758. Min Range: -0.5758

Max Act: 0.4559. Min Act: -0.0000

Data Index: 211482 (The Pile)

Max Activating Token Index: 535

Text #4

Max Range: 0.5758. Min Range: -0.5758

Max Act: 0.4049. Min Act: -0.0000

Data Index: 1604235 (The Pile)

Max Activating Token Index: 716

Text #5

Max Range: 0.5758. Min Range: -0.5758

Max Act: 0.3905. Min Act: -0.0000

Data Index: 385781 (The Pile)

Max Activating Token Index: 928

Text #6

Max Range: 0.5758. Min Range: -0.5758

Max Act: 0.4162. Min Act: -0.0000

Data Index: 143760 (The Pile)

Max Activating Token Index: 469

Text #7

Max Range: 0.5758. Min Range: -0.5758

Max Act: 0.3978. Min Act: -0.0000

Data Index: 1046161 (The Pile)

Max Activating Token Index: 751

Text #8

Max Range: 0.5758. Min Range: -0.5758

Max Act: 0.3949. Min Act: -0.0000

Data Index: 1754670 (The Pile)

Max Activating Token Index: 706

Text #9

Max Range: 0.5758. Min Range: -0.5758

Max Act: 0.4032. Min Act: -0.0000

Data Index: 1319517 (The Pile)

Max Activating Token Index: 44

Text #10

Max Range: 0.5758. Min Range: -0.5758

Max Act: 0.3880. Min Act: -0.0000

Data Index: 1679182 (The Pile)

Max Activating Token Index: 803

Text #11

Max Range: 0.5758. Min Range: -0.5758

Max Act: 0.3835. Min Act: -0.0000

Data Index: 390429 (The Pile)

Max Activating Token Index: 1004

Text #12

Max Range: 0.5758. Min Range: -0.5758

Max Act: 0.3706. Min Act: -0.0000

Data Index: 1538106 (The Pile)

Max Activating Token Index: 400

Text #13

Max Range: 0.5758. Min Range: -0.5758

Max Act: 0.3783. Min Act: -0.0000

Data Index: 549376 (The Pile)

Max Activating Token Index: 143

Text #14

Max Range: 0.5758. Min Range: -0.5758

Max Act: 0.3771. Min Act: -0.0000

Data Index: 728225 (The Pile)

Max Activating Token Index: 995

Text #15

Max Range: 0.5758. Min Range: -0.5758

Max Act: 0.3498. Min Act: -0.0000

Data Index: 635081 (The Pile)

Max Activating Token Index: 896

Text #16

Max Range: 0.5758. Min Range: -0.5758

Max Act: 0.3437. Min Act: -0.0000

Data Index: 1308266 (The Pile)

Max Activating Token Index: 730

Text #17

Max Range: 0.5758. Min Range: -0.5758

Max Act: 0.3614. Min Act: -0.0000

Data Index: 1719085 (The Pile)

Max Activating Token Index: 588

Text #18

Max Range: 0.5758. Min Range: -0.5758

Max Act: 0.3613. Min Act: -0.0000

Data Index: 49454 (The Pile)

Max Activating Token Index: 125

Text #19

Max Range: 0.5758. Min Range: -0.5758

Max Act: 0.3598. Min Act: -0.0000

Data Index: 1158856 (The Pile)

Max Activating Token Index: 635