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

Dataset: The Pile

Neuron 353 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: 7.1232. Min Range: -7.1232

Max Act: 7.1065. Min Act: -0.0000

Data Index: 877875 (The Pile)

Max Activating Token Index: 675

Text #1

Max Range: 7.1232. Min Range: -7.1232

Max Act: 7.1232. Min Act: -0.0000

Data Index: 1122949 (The Pile)

Max Activating Token Index: 240

Text #2

Max Range: 7.1232. Min Range: -7.1232

Max Act: 7.1052. Min Act: -0.0000

Data Index: 1894672 (The Pile)

Max Activating Token Index: 679

Text #3

Max Range: 7.1232. Min Range: -7.1232

Max Act: 6.8095. Min Act: -0.0000

Data Index: 1165092 (The Pile)

Max Activating Token Index: 624

Text #4

Max Range: 7.1232. Min Range: -7.1232

Max Act: 6.9674. Min Act: -0.0000

Data Index: 1914605 (The Pile)

Max Activating Token Index: 892

Text #5

Max Range: 7.1232. Min Range: -7.1232

Max Act: 6.8626. Min Act: -0.0000

Data Index: 1129033 (The Pile)

Max Activating Token Index: 799

Text #6

Max Range: 7.1232. Min Range: -7.1232

Max Act: 6.9414. Min Act: -0.0000

Data Index: 349031 (The Pile)

Max Activating Token Index: 762

Text #7

Max Range: 7.1232. Min Range: -7.1232

Max Act: 6.8969. Min Act: -0.0000

Data Index: 956294 (The Pile)

Max Activating Token Index: 738

Text #8

Max Range: 7.1232. Min Range: -7.1232

Max Act: 6.9666. Min Act: -0.0000

Data Index: 108683 (The Pile)

Max Activating Token Index: 124

Text #9

Max Range: 7.1232. Min Range: -7.1232

Max Act: 6.9060. Min Act: -0.0000

Data Index: 564878 (The Pile)

Max Activating Token Index: 254

Text #10

Max Range: 7.1232. Min Range: -7.1232

Max Act: 6.9778. Min Act: -0.0000

Data Index: 1936194 (The Pile)

Max Activating Token Index: 139

Text #11

Max Range: 7.1232. Min Range: -7.1232

Max Act: 7.1054. Min Act: -0.0000

Data Index: 1734830 (The Pile)

Max Activating Token Index: 658

Text #12

Max Range: 7.1232. Min Range: -7.1232

Max Act: 6.6803. Min Act: -0.0000

Data Index: 1059496 (The Pile)

Max Activating Token Index: 139

Text #13

Max Range: 7.1232. Min Range: -7.1232

Max Act: 6.8013. Min Act: -0.0000

Data Index: 1998980 (The Pile)

Max Activating Token Index: 446

Text #14

Max Range: 7.1232. Min Range: -7.1232

Max Act: 6.6086. Min Act: -0.0000

Data Index: 1659308 (The Pile)

Max Activating Token Index: 487

Text #15

Max Range: 7.1232. Min Range: -7.1232

Max Act: 6.7986. Min Act: -0.0000

Data Index: 1155043 (The Pile)

Max Activating Token Index: 359

Text #16

Max Range: 7.1232. Min Range: -7.1232

Max Act: 6.9931. Min Act: -0.0000

Data Index: 1420998 (The Pile)

Max Activating Token Index: 768

Text #17

Max Range: 7.1232. Min Range: -7.1232

Max Act: 6.7895. Min Act: -0.0000

Data Index: 164733 (The Pile)

Max Activating Token Index: 512

Text #18

Max Range: 7.1232. Min Range: -7.1232

Max Act: 6.7729. Min Act: -0.0000

Data Index: 917381 (The Pile)

Max Activating Token Index: 128

Text #19

Max Range: 7.1232. Min Range: -7.1232

Max Act: 6.5548. Min Act: -0.0000

Data Index: 1559769 (The Pile)

Max Activating Token Index: 347