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

Dataset: The Pile

Neuron 1952 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: 8.1057. Min Range: -8.1057

Max Act: 8.1057. Min Act: -0.0000

Data Index: 1652500 (The Pile)

Max Activating Token Index: 797

Text #1

Max Range: 8.1057. Min Range: -8.1057

Max Act: 5.7665. Min Act: -0.0000

Data Index: 1472780 (The Pile)

Max Activating Token Index: 721

Text #2

Max Range: 8.1057. Min Range: -8.1057

Max Act: 4.2786. Min Act: -0.0000

Data Index: 628008 (The Pile)

Max Activating Token Index: 686

Text #3

Max Range: 8.1057. Min Range: -8.1057

Max Act: 4.4501. Min Act: -0.0000

Data Index: 570698 (The Pile)

Max Activating Token Index: 646

Text #4

Max Range: 8.1057. Min Range: -8.1057

Max Act: 4.2662. Min Act: -0.0000

Data Index: 205291 (The Pile)

Max Activating Token Index: 1011

Text #5

Max Range: 8.1057. Min Range: -8.1057

Max Act: 3.1688. Min Act: -0.0000

Data Index: 1493429 (The Pile)

Max Activating Token Index: 696

Text #6

Max Range: 8.1057. Min Range: -8.1057

Max Act: 3.5853. Min Act: -0.0000

Data Index: 1472918 (The Pile)

Max Activating Token Index: 773

Text #7

Max Range: 8.1057. Min Range: -8.1057

Max Act: 4.3672. Min Act: -0.0000

Data Index: 1520763 (The Pile)

Max Activating Token Index: 932

Text #8

Max Range: 8.1057. Min Range: -8.1057

Max Act: 3.7775. Min Act: -0.0000

Data Index: 341471 (The Pile)

Max Activating Token Index: 780

Text #9

Max Range: 8.1057. Min Range: -8.1057

Max Act: 3.6724. Min Act: -0.0000

Data Index: 1474826 (The Pile)

Max Activating Token Index: 785

Text #10

Max Range: 8.1057. Min Range: -8.1057

Max Act: 3.3950. Min Act: -0.0000

Data Index: 590487 (The Pile)

Max Activating Token Index: 1003

Text #11

Max Range: 8.1057. Min Range: -8.1057

Max Act: 3.5434. Min Act: -0.0000

Data Index: 1028348 (The Pile)

Max Activating Token Index: 773

Text #12

Max Range: 8.1057. Min Range: -8.1057

Max Act: 3.7191. Min Act: -0.0000

Data Index: 456347 (The Pile)

Max Activating Token Index: 479

Text #13

Max Range: 8.1057. Min Range: -8.1057

Max Act: 3.2394. Min Act: -0.0000

Data Index: 729879 (The Pile)

Max Activating Token Index: 615

Text #14

Max Range: 8.1057. Min Range: -8.1057

Max Act: 3.5823. Min Act: -0.0000

Data Index: 1157993 (The Pile)

Max Activating Token Index: 307

Text #15

Max Range: 8.1057. Min Range: -8.1057

Max Act: 4.0330. Min Act: -0.0000

Data Index: 306772 (The Pile)

Max Activating Token Index: 719

Text #16

Max Range: 8.1057. Min Range: -8.1057

Max Act: 3.3616. Min Act: -0.0000

Data Index: 1628686 (The Pile)

Max Activating Token Index: 123

Text #17

Max Range: 8.1057. Min Range: -8.1057

Max Act: 3.7482. Min Act: -0.0000

Data Index: 1637454 (The Pile)

Max Activating Token Index: 491

Text #18

Max Range: 8.1057. Min Range: -8.1057

Max Act: 3.6281. Min Act: -0.0000

Data Index: 468963 (The Pile)

Max Activating Token Index: 736

Text #19

Max Range: 8.1057. Min Range: -8.1057

Max Act: 3.5328. Min Act: -0.0000

Data Index: 1620930 (The Pile)

Max Activating Token Index: 588