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

Dataset: The Pile

Neuron 1503 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: 0.0924. Min Range: -0.0924

Max Act: 0.0897. Min Act: -0.0000

Data Index: 134682 (The Pile)

Max Activating Token Index: 257

Text #1

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0924. Min Act: -0.0000

Data Index: 151642 (The Pile)

Max Activating Token Index: 45

Text #2

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0862. Min Act: -0.0000

Data Index: 188646 (The Pile)

Max Activating Token Index: 261

Text #3

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0827. Min Act: -0.0000

Data Index: 1000593 (The Pile)

Max Activating Token Index: 216

Text #4

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0773. Min Act: -0.0000

Data Index: 1421924 (The Pile)

Max Activating Token Index: 118

Text #5

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0829. Min Act: -0.0000

Data Index: 1948774 (The Pile)

Max Activating Token Index: 1003

Text #6

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0847. Min Act: -0.0000

Data Index: 1569999 (The Pile)

Max Activating Token Index: 527

Text #7

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0777. Min Act: -0.0000

Data Index: 1707620 (The Pile)

Max Activating Token Index: 22

Text #8

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0741. Min Act: -0.0000

Data Index: 1830512 (The Pile)

Max Activating Token Index: 123

Text #9

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0797. Min Act: -0.0000

Data Index: 821658 (The Pile)

Max Activating Token Index: 386

Text #10

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0849. Min Act: -0.0000

Data Index: 807443 (The Pile)

Max Activating Token Index: 154

Text #11

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0788. Min Act: -0.0000

Data Index: 349389 (The Pile)

Max Activating Token Index: 69

Text #12

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0782. Min Act: -0.0000

Data Index: 125082 (The Pile)

Max Activating Token Index: 147

Text #13

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0807. Min Act: -0.0000

Data Index: 661469 (The Pile)

Max Activating Token Index: 389

Text #14

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0743. Min Act: -0.0000

Data Index: 1864189 (The Pile)

Max Activating Token Index: 230

Text #15

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0753. Min Act: -0.0000

Data Index: 556958 (The Pile)

Max Activating Token Index: 28

Text #16

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0697. Min Act: -0.0000

Data Index: 1825491 (The Pile)

Max Activating Token Index: 164

Text #17

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0689. Min Act: -0.0000

Data Index: 1991722 (The Pile)

Max Activating Token Index: 382

Text #18

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0696. Min Act: -0.0000

Data Index: 843960 (The Pile)

Max Activating Token Index: 144

Text #19

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0741. Min Act: -0.0000

Data Index: 217535 (The Pile)

Max Activating Token Index: 417