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

Dataset: The Pile

Neuron 4400 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: 0.3624. Min Range: -0.3624

Max Act: 0.3624. Min Act: -0.0000

Data Index: 178620 (The Pile)

Max Activating Token Index: 615

Text #1

Max Range: 0.3624. Min Range: -0.3624

Max Act: 0.3534. Min Act: -0.0000

Data Index: 745712 (The Pile)

Max Activating Token Index: 548

Text #2

Max Range: 0.3624. Min Range: -0.3624

Max Act: 0.3487. Min Act: -0.0000

Data Index: 161506 (The Pile)

Max Activating Token Index: 454

Text #3

Max Range: 0.3624. Min Range: -0.3624

Max Act: 0.3034. Min Act: -0.0000

Data Index: 1466130 (The Pile)

Max Activating Token Index: 788

Text #4

Max Range: 0.3624. Min Range: -0.3624

Max Act: 0.2898. Min Act: -0.0000

Data Index: 108821 (The Pile)

Max Activating Token Index: 613

Text #5

Max Range: 0.3624. Min Range: -0.3624

Max Act: 0.2981. Min Act: -0.0000

Data Index: 1513327 (The Pile)

Max Activating Token Index: 272

Text #6

Max Range: 0.3624. Min Range: -0.3624

Max Act: 0.2973. Min Act: -0.0000

Data Index: 1080816 (The Pile)

Max Activating Token Index: 549

Text #7

Max Range: 0.3624. Min Range: -0.3624

Max Act: 0.2951. Min Act: -0.0000

Data Index: 1245900 (The Pile)

Max Activating Token Index: 561

Text #8

Max Range: 0.3624. Min Range: -0.3624

Max Act: 0.2924. Min Act: -0.0000

Data Index: 482518 (The Pile)

Max Activating Token Index: 685

Text #9

Max Range: 0.3624. Min Range: -0.3624

Max Act: 0.3010. Min Act: -0.0000

Data Index: 1173310 (The Pile)

Max Activating Token Index: 899

Text #10

Max Range: 0.3624. Min Range: -0.3624

Max Act: 0.2850. Min Act: -0.0000

Data Index: 765795 (The Pile)

Max Activating Token Index: 973

Text #11

Max Range: 0.3624. Min Range: -0.3624

Max Act: 0.2725. Min Act: -0.0000

Data Index: 1137859 (The Pile)

Max Activating Token Index: 580

Text #12

Max Range: 0.3624. Min Range: -0.3624

Max Act: 0.2678. Min Act: -0.0000

Data Index: 981060 (The Pile)

Max Activating Token Index: 227

Text #13

Max Range: 0.3624. Min Range: -0.3624

Max Act: 0.2748. Min Act: -0.0000

Data Index: 17084 (The Pile)

Max Activating Token Index: 397

Text #14

Max Range: 0.3624. Min Range: -0.3624

Max Act: 0.2742. Min Act: -0.0000

Data Index: 1032949 (The Pile)

Max Activating Token Index: 637

Text #15

Max Range: 0.3624. Min Range: -0.3624

Max Act: 0.2716. Min Act: -0.0000

Data Index: 331100 (The Pile)

Max Activating Token Index: 205

Text #16

Max Range: 0.3624. Min Range: -0.3624

Max Act: 0.2664. Min Act: -0.0000

Data Index: 1975710 (The Pile)

Max Activating Token Index: 868

Text #17

Max Range: 0.3624. Min Range: -0.3624

Max Act: 0.2618. Min Act: -0.0000

Data Index: 1707599 (The Pile)

Max Activating Token Index: 402

Text #18

Max Range: 0.3624. Min Range: -0.3624

Max Act: 0.2579. Min Act: -0.0000

Data Index: 821033 (The Pile)

Max Activating Token Index: 776

Text #19

Max Range: 0.3624. Min Range: -0.3624

Max Act: 0.2578. Min Act: -0.0000

Data Index: 136818 (The Pile)

Max Activating Token Index: 227