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

Dataset: The Pile

Neuron 1778 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: 1.5972. Min Range: -1.5972

Max Act: 1.3879. Min Act: -0.0000

Data Index: 57074 (The Pile)

Max Activating Token Index: 865

Text #1

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.4578. Min Act: -0.0000

Data Index: 621755 (The Pile)

Max Activating Token Index: 989

Text #2

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.5025. Min Act: -0.0000

Data Index: 457993 (The Pile)

Max Activating Token Index: 886

Text #3

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.5017. Min Act: -0.0000

Data Index: 1414544 (The Pile)

Max Activating Token Index: 960

Text #4

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.5972. Min Act: -0.0000

Data Index: 1495177 (The Pile)

Max Activating Token Index: 942

Text #5

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.5130. Min Act: -0.0000

Data Index: 560751 (The Pile)

Max Activating Token Index: 1021

Text #6

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.3031. Min Act: -0.0000

Data Index: 210023 (The Pile)

Max Activating Token Index: 755

Text #7

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.2884. Min Act: -0.0000

Data Index: 1284101 (The Pile)

Max Activating Token Index: 1002

Text #8

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.4553. Min Act: -0.0000

Data Index: 726308 (The Pile)

Max Activating Token Index: 638

Text #9

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.2540. Min Act: -0.0000

Data Index: 272121 (The Pile)

Max Activating Token Index: 696

Text #10

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.3037. Min Act: -0.0000

Data Index: 1594958 (The Pile)

Max Activating Token Index: 834

Text #11

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.3080. Min Act: -0.0000

Data Index: 1517017 (The Pile)

Max Activating Token Index: 192

Text #12

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.3466. Min Act: -0.0000

Data Index: 1087262 (The Pile)

Max Activating Token Index: 934

Text #13

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.2427. Min Act: -0.0000

Data Index: 1483289 (The Pile)

Max Activating Token Index: 668

Text #14

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.2503. Min Act: -0.0000

Data Index: 1076835 (The Pile)

Max Activating Token Index: 379

Text #15

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.2110. Min Act: -0.0000

Data Index: 1266618 (The Pile)

Max Activating Token Index: 610

Text #16

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.2137. Min Act: -0.0000

Data Index: 355090 (The Pile)

Max Activating Token Index: 872

Text #17

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.2376. Min Act: -0.0000

Data Index: 1513032 (The Pile)

Max Activating Token Index: 841

Text #18

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.2202. Min Act: -0.0000

Data Index: 1481927 (The Pile)

Max Activating Token Index: 1005

Text #19

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.2266. Min Act: -0.0000

Data Index: 15672 (The Pile)

Max Activating Token Index: 925