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

Dataset: The Pile

Neuron 4007 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1999. Min Range: -2.1999

Max Act: 2.1999. Min Act: -0.0000

Data Index: 861649 (The Pile)

Max Activating Token Index: 916

Text #1

Max Range: 2.1999. Min Range: -2.1999

Max Act: 2.1041. Min Act: -0.0000

Data Index: 201232 (The Pile)

Max Activating Token Index: 26

Text #2

Max Range: 2.1999. Min Range: -2.1999

Max Act: 1.9624. Min Act: -0.0000

Data Index: 1162976 (The Pile)

Max Activating Token Index: 484

Text #3

Max Range: 2.1999. Min Range: -2.1999

Max Act: 1.5318. Min Act: -0.0000

Data Index: 1170141 (The Pile)

Max Activating Token Index: 1005

Text #4

Max Range: 2.1999. Min Range: -2.1999

Max Act: 1.7920. Min Act: -0.0000

Data Index: 1861444 (The Pile)

Max Activating Token Index: 660

Text #5

Max Range: 2.1999. Min Range: -2.1999

Max Act: 1.6947. Min Act: -0.0000

Data Index: 1139244 (The Pile)

Max Activating Token Index: 898

Text #6

Max Range: 2.1999. Min Range: -2.1999

Max Act: 1.6654. Min Act: -0.0000

Data Index: 1363832 (The Pile)

Max Activating Token Index: 967

Text #7

Max Range: 2.1999. Min Range: -2.1999

Max Act: 1.5370. Min Act: -0.0000

Data Index: 1370596 (The Pile)

Max Activating Token Index: 743

Text #8

Max Range: 2.1999. Min Range: -2.1999

Max Act: 1.7146. Min Act: -0.0000

Data Index: 1918281 (The Pile)

Max Activating Token Index: 141

Text #9

Max Range: 2.1999. Min Range: -2.1999

Max Act: 1.5786. Min Act: -0.0000

Data Index: 1311576 (The Pile)

Max Activating Token Index: 954

Text #10

Max Range: 2.1999. Min Range: -2.1999

Max Act: 1.5913. Min Act: -0.0000

Data Index: 1534222 (The Pile)

Max Activating Token Index: 1016

Text #11

Max Range: 2.1999. Min Range: -2.1999

Max Act: 1.4100. Min Act: -0.0000

Data Index: 1572315 (The Pile)

Max Activating Token Index: 956

Text #12

Max Range: 2.1999. Min Range: -2.1999

Max Act: 1.4921. Min Act: -0.0000

Data Index: 1230206 (The Pile)

Max Activating Token Index: 946

Text #13

Max Range: 2.1999. Min Range: -2.1999

Max Act: 1.4805. Min Act: -0.0000

Data Index: 895930 (The Pile)

Max Activating Token Index: 978

Text #14

Max Range: 2.1999. Min Range: -2.1999

Max Act: 1.6583. Min Act: -0.0000

Data Index: 1729781 (The Pile)

Max Activating Token Index: 1009

Text #15

Max Range: 2.1999. Min Range: -2.1999

Max Act: 1.5490. Min Act: -0.0000

Data Index: 1719491 (The Pile)

Max Activating Token Index: 1017

Text #16

Max Range: 2.1999. Min Range: -2.1999

Max Act: 1.5412. Min Act: -0.0000

Data Index: 1657683 (The Pile)

Max Activating Token Index: 80

Text #17

Max Range: 2.1999. Min Range: -2.1999

Max Act: 1.3574. Min Act: -0.0000

Data Index: 1177584 (The Pile)

Max Activating Token Index: 1013

Text #18

Max Range: 2.1999. Min Range: -2.1999

Max Act: 1.5100. Min Act: -0.0000

Data Index: 1674414 (The Pile)

Max Activating Token Index: 782

Text #19

Max Range: 2.1999. Min Range: -2.1999

Max Act: 1.5494. Min Act: -0.0000

Data Index: 633724 (The Pile)

Max Activating Token Index: 908