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

Dataset: The Pile

Neuron 439 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: 0.1054. Min Range: -0.1054

Max Act: 0.1054. Min Act: -0.0000

Data Index: 114844 (The Pile)

Max Activating Token Index: 824

Text #1

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.1033. Min Act: -0.0000

Data Index: 1017616 (The Pile)

Max Activating Token Index: 466

Text #2

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0913. Min Act: -0.0000

Data Index: 1652152 (The Pile)

Max Activating Token Index: 132

Text #3

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0910. Min Act: -0.0000

Data Index: 1971527 (The Pile)

Max Activating Token Index: 852

Text #4

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0833. Min Act: -0.0000

Data Index: 719909 (The Pile)

Max Activating Token Index: 310

Text #5

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0823. Min Act: -0.0000

Data Index: 932065 (The Pile)

Max Activating Token Index: 744

Text #6

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0780. Min Act: -0.0000

Data Index: 1083330 (The Pile)

Max Activating Token Index: 351

Text #7

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0745. Min Act: -0.0000

Data Index: 227835 (The Pile)

Max Activating Token Index: 953

Text #8

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0711. Min Act: -0.0000

Data Index: 1811712 (The Pile)

Max Activating Token Index: 925

Text #9

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0743. Min Act: -0.0000

Data Index: 642134 (The Pile)

Max Activating Token Index: 617

Text #10

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0824. Min Act: -0.0000

Data Index: 1534068 (The Pile)

Max Activating Token Index: 251

Text #11

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0794. Min Act: -0.0000

Data Index: 1730983 (The Pile)

Max Activating Token Index: 934

Text #12

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0697. Min Act: -0.0000

Data Index: 603739 (The Pile)

Max Activating Token Index: 167

Text #13

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0696. Min Act: -0.0000

Data Index: 1375212 (The Pile)

Max Activating Token Index: 794

Text #14

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0736. Min Act: -0.0000

Data Index: 1188454 (The Pile)

Max Activating Token Index: 254

Text #15

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0716. Min Act: -0.0000

Data Index: 126347 (The Pile)

Max Activating Token Index: 982

Text #16

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0703. Min Act: -0.0000

Data Index: 1718934 (The Pile)

Max Activating Token Index: 408

Text #17

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0698. Min Act: -0.0000

Data Index: 1793286 (The Pile)

Max Activating Token Index: 398

Text #18

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0728. Min Act: -0.0000

Data Index: 1179147 (The Pile)

Max Activating Token Index: 130

Text #19

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0664. Min Act: -0.0000

Data Index: 1220171 (The Pile)

Max Activating Token Index: 1011