Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 859 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.2926. Min Range: -1.2926

Max Act: 1.2926. Min Act: -0.0000

Data Index: 500065 (The Pile)

Max Activating Token Index: 742

Text #1

Max Range: 1.2926. Min Range: -1.2926

Max Act: 1.1816. Min Act: -0.0000

Data Index: 470156 (The Pile)

Max Activating Token Index: 779

Text #2

Max Range: 1.2926. Min Range: -1.2926

Max Act: 1.1214. Min Act: 0.0000

Data Index: 1717623 (The Pile)

Max Activating Token Index: 804

Text #3

Max Range: 1.2926. Min Range: -1.2926

Max Act: 1.1215. Min Act: -0.0000

Data Index: 342326 (The Pile)

Max Activating Token Index: 686

Text #4

Max Range: 1.2926. Min Range: -1.2926

Max Act: 1.0787. Min Act: -0.0000

Data Index: 1566247 (The Pile)

Max Activating Token Index: 470

Text #5

Max Range: 1.2926. Min Range: -1.2926

Max Act: 1.0734. Min Act: -0.0000

Data Index: 112059 (The Pile)

Max Activating Token Index: 109

Text #6

Max Range: 1.2926. Min Range: -1.2926

Max Act: 1.0560. Min Act: -0.0000

Data Index: 1609438 (The Pile)

Max Activating Token Index: 109

Text #7

Max Range: 1.2926. Min Range: -1.2926

Max Act: 1.0088. Min Act: -0.0000

Data Index: 1132340 (The Pile)

Max Activating Token Index: 30

Text #8

Max Range: 1.2926. Min Range: -1.2926

Max Act: 1.0056. Min Act: 0.0000

Data Index: 1745466 (The Pile)

Max Activating Token Index: 864

Text #9

Max Range: 1.2926. Min Range: -1.2926

Max Act: 0.9727. Min Act: -0.0000

Data Index: 1210327 (The Pile)

Max Activating Token Index: 723

Text #10

Max Range: 1.2926. Min Range: -1.2926

Max Act: 0.9968. Min Act: -0.0000

Data Index: 1095736 (The Pile)

Max Activating Token Index: 131

Text #11

Max Range: 1.2926. Min Range: -1.2926

Max Act: 0.9606. Min Act: -0.0000

Data Index: 1562716 (The Pile)

Max Activating Token Index: 381

Text #12

Max Range: 1.2926. Min Range: -1.2926

Max Act: 0.9891. Min Act: -0.0000

Data Index: 1803194 (The Pile)

Max Activating Token Index: 313

Text #13

Max Range: 1.2926. Min Range: -1.2926

Max Act: 0.9344. Min Act: -0.0000

Data Index: 148442 (The Pile)

Max Activating Token Index: 772

Text #14

Max Range: 1.2926. Min Range: -1.2926

Max Act: 0.9287. Min Act: -0.0000

Data Index: 478533 (The Pile)

Max Activating Token Index: 378

Text #15

Max Range: 1.2926. Min Range: -1.2926

Max Act: 0.9592. Min Act: -0.0000

Data Index: 1306083 (The Pile)

Max Activating Token Index: 214

Text #16

Max Range: 1.2926. Min Range: -1.2926

Max Act: 0.9287. Min Act: -0.0000

Data Index: 354075 (The Pile)

Max Activating Token Index: 527

Text #17

Max Range: 1.2926. Min Range: -1.2926

Max Act: 0.9480. Min Act: -0.0000

Data Index: 1725325 (The Pile)

Max Activating Token Index: 95

Text #18

Max Range: 1.2926. Min Range: -1.2926

Max Act: 0.8816. Min Act: 0.0000

Data Index: 22857 (The Pile)

Max Activating Token Index: 651

Text #19

Max Range: 1.2926. Min Range: -1.2926

Max Act: 0.9574. Min Act: -0.0000

Data Index: 790627 (The Pile)

Max Activating Token Index: 918