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

Dataset: The Pile

Neuron 1356 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: 0.1640. Min Range: -0.1640

Max Act: 0.1640. Min Act: -0.0000

Data Index: 900138 (The Pile)

Max Activating Token Index: 581

Text #1

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1322. Min Act: -0.0000

Data Index: 1549780 (The Pile)

Max Activating Token Index: 712

Text #2

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1218. Min Act: -0.0000

Data Index: 1069398 (The Pile)

Max Activating Token Index: 775

Text #3

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1136. Min Act: -0.0000

Data Index: 633574 (The Pile)

Max Activating Token Index: 504

Text #4

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1140. Min Act: -0.0000

Data Index: 1437074 (The Pile)

Max Activating Token Index: 688

Text #5

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1036. Min Act: -0.0000

Data Index: 93522 (The Pile)

Max Activating Token Index: 887

Text #6

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1078. Min Act: -0.0000

Data Index: 1322762 (The Pile)

Max Activating Token Index: 602

Text #7

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.0933. Min Act: -0.0000

Data Index: 1633747 (The Pile)

Max Activating Token Index: 167

Text #8

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1029. Min Act: -0.0000

Data Index: 1314618 (The Pile)

Max Activating Token Index: 44

Text #9

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.0893. Min Act: -0.0000

Data Index: 1254775 (The Pile)

Max Activating Token Index: 233

Text #10

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1055. Min Act: -0.0000

Data Index: 443256 (The Pile)

Max Activating Token Index: 753

Text #11

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.0959. Min Act: -0.0000

Data Index: 797465 (The Pile)

Max Activating Token Index: 263

Text #12

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.0931. Min Act: -0.0000

Data Index: 1769980 (The Pile)

Max Activating Token Index: 518

Text #13

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.0911. Min Act: -0.0000

Data Index: 621948 (The Pile)

Max Activating Token Index: 258

Text #14

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1050. Min Act: -0.0000

Data Index: 798379 (The Pile)

Max Activating Token Index: 876

Text #15

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.0875. Min Act: -0.0000

Data Index: 247674 (The Pile)

Max Activating Token Index: 353

Text #16

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.0889. Min Act: -0.0000

Data Index: 195245 (The Pile)

Max Activating Token Index: 264

Text #17

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.0852. Min Act: -0.0000

Data Index: 232190 (The Pile)

Max Activating Token Index: 13

Text #18

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1017. Min Act: -0.0000

Data Index: 1150844 (The Pile)

Max Activating Token Index: 993

Text #19

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.0862. Min Act: -0.0000

Data Index: 849611 (The Pile)

Max Activating Token Index: 478