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

Dataset: The Pile

Neuron 2550 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.8058. Min Act: -0.0000

Data Index: 316980 (The Pile)

Max Activating Token Index: 326

Text #1

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.7531. Min Act: -0.0000

Data Index: 1932849 (The Pile)

Max Activating Token Index: 509

Text #2

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.7907. Min Act: -0.0000

Data Index: 366374 (The Pile)

Max Activating Token Index: 5

Text #3

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.8096. Min Act: -0.0000

Data Index: 1560049 (The Pile)

Max Activating Token Index: 69

Text #4

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.7931. Min Act: -0.0000

Data Index: 752825 (The Pile)

Max Activating Token Index: 691

Text #5

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.7697. Min Act: -0.0000

Data Index: 19036 (The Pile)

Max Activating Token Index: 18

Text #6

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.7537. Min Act: -0.0000

Data Index: 1907368 (The Pile)

Max Activating Token Index: 327

Text #7

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.7029. Min Act: -0.0000

Data Index: 127185 (The Pile)

Max Activating Token Index: 13

Text #8

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.7162. Min Act: -0.0000

Data Index: 1567967 (The Pile)

Max Activating Token Index: 519

Text #9

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.7195. Min Act: -0.0000

Data Index: 969457 (The Pile)

Max Activating Token Index: 519

Text #10

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.6919. Min Act: -0.0000

Data Index: 1068100 (The Pile)

Max Activating Token Index: 1009

Text #11

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.6895. Min Act: -0.0000

Data Index: 1624899 (The Pile)

Max Activating Token Index: 840

Text #12

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.6995. Min Act: -0.0000

Data Index: 1511523 (The Pile)

Max Activating Token Index: 540

Text #13

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.6730. Min Act: -0.0000

Data Index: 1005524 (The Pile)

Max Activating Token Index: 258

Text #14

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.6924. Min Act: -0.0000

Data Index: 1393088 (The Pile)

Max Activating Token Index: 609

Text #15

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.6738. Min Act: -0.0000

Data Index: 1102394 (The Pile)

Max Activating Token Index: 268

Text #16

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.6686. Min Act: -0.0000

Data Index: 889438 (The Pile)

Max Activating Token Index: 525

Text #17

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.6830. Min Act: -0.0000

Data Index: 76943 (The Pile)

Max Activating Token Index: 583

Text #18

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.6436. Min Act: -0.0000

Data Index: 334420 (The Pile)

Max Activating Token Index: 176

Text #19

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.7051. Min Act: -0.0000

Data Index: 1958766 (The Pile)

Max Activating Token Index: 46