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

Dataset: The Pile

Neuron 3711 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7741. Min Range: -1.7741

Max Act: 1.7741. Min Act: -0.0000

Data Index: 219888 (The Pile)

Max Activating Token Index: 549

Text #1

Max Range: 1.7741. Min Range: -1.7741

Max Act: 1.4209. Min Act: -0.0000

Data Index: 1943895 (The Pile)

Max Activating Token Index: 40

Text #2

Max Range: 1.7741. Min Range: -1.7741

Max Act: 1.4959. Min Act: -0.0000

Data Index: 379914 (The Pile)

Max Activating Token Index: 282

Text #3

Max Range: 1.7741. Min Range: -1.7741

Max Act: 1.6743. Min Act: -0.0000

Data Index: 30933 (The Pile)

Max Activating Token Index: 678

Text #4

Max Range: 1.7741. Min Range: -1.7741

Max Act: 1.5077. Min Act: -0.0000

Data Index: 1858963 (The Pile)

Max Activating Token Index: 804

Text #5

Max Range: 1.7741. Min Range: -1.7741

Max Act: 1.3891. Min Act: -0.0000

Data Index: 1309481 (The Pile)

Max Activating Token Index: 377

Text #6

Max Range: 1.7741. Min Range: -1.7741

Max Act: 1.5828. Min Act: -0.0000

Data Index: 618644 (The Pile)

Max Activating Token Index: 56

Text #7

Max Range: 1.7741. Min Range: -1.7741

Max Act: 1.4486. Min Act: -0.0000

Data Index: 1015685 (The Pile)

Max Activating Token Index: 235

Text #8

Max Range: 1.7741. Min Range: -1.7741

Max Act: 1.4105. Min Act: -0.0000

Data Index: 1639107 (The Pile)

Max Activating Token Index: 677

Text #9

Max Range: 1.7741. Min Range: -1.7741

Max Act: 1.4299. Min Act: -0.0000

Data Index: 1037702 (The Pile)

Max Activating Token Index: 103

Text #10

Max Range: 1.7741. Min Range: -1.7741

Max Act: 1.4803. Min Act: -0.0000

Data Index: 160523 (The Pile)

Max Activating Token Index: 24

Text #11

Max Range: 1.7741. Min Range: -1.7741

Max Act: 1.3807. Min Act: -0.0000

Data Index: 696383 (The Pile)

Max Activating Token Index: 203

Text #12

Max Range: 1.7741. Min Range: -1.7741

Max Act: 1.3546. Min Act: -0.0000

Data Index: 179792 (The Pile)

Max Activating Token Index: 221

Text #13

Max Range: 1.7741. Min Range: -1.7741

Max Act: 1.3002. Min Act: -0.0000

Data Index: 1044570 (The Pile)

Max Activating Token Index: 157

Text #14

Max Range: 1.7741. Min Range: -1.7741

Max Act: 1.1537. Min Act: -0.0000

Data Index: 1185166 (The Pile)

Max Activating Token Index: 964

Text #15

Max Range: 1.7741. Min Range: -1.7741

Max Act: 1.1993. Min Act: -0.0000

Data Index: 938646 (The Pile)

Max Activating Token Index: 393

Text #16

Max Range: 1.7741. Min Range: -1.7741

Max Act: 1.2088. Min Act: -0.0000

Data Index: 495139 (The Pile)

Max Activating Token Index: 680

Text #17

Max Range: 1.7741. Min Range: -1.7741

Max Act: 1.1835. Min Act: 0.0000

Data Index: 356036 (The Pile)

Max Activating Token Index: 965

Text #18

Max Range: 1.7741. Min Range: -1.7741

Max Act: 1.1855. Min Act: -0.0000

Data Index: 204126 (The Pile)

Max Activating Token Index: 900

Text #19

Max Range: 1.7741. Min Range: -1.7741

Max Act: 1.1606. Min Act: -0.0000

Data Index: 803885 (The Pile)

Max Activating Token Index: 124