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

Dataset: The Pile

Neuron 1143 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: 0.1060. Min Range: -0.1060

Max Act: 0.0982. Min Act: -0.0000

Data Index: 1555680 (The Pile)

Max Activating Token Index: 112

Text #1

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.1060. Min Act: -0.0000

Data Index: 290727 (The Pile)

Max Activating Token Index: 405

Text #2

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0935. Min Act: -0.0000

Data Index: 729495 (The Pile)

Max Activating Token Index: 664

Text #3

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0889. Min Act: -0.0000

Data Index: 958181 (The Pile)

Max Activating Token Index: 96

Text #4

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0813. Min Act: -0.0000

Data Index: 838305 (The Pile)

Max Activating Token Index: 588

Text #5

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0762. Min Act: -0.0000

Data Index: 938117 (The Pile)

Max Activating Token Index: 217

Text #6

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0734. Min Act: -0.0000

Data Index: 81847 (The Pile)

Max Activating Token Index: 525

Text #7

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0717. Min Act: -0.0000

Data Index: 268954 (The Pile)

Max Activating Token Index: 873

Text #8

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0670. Min Act: -0.0000

Data Index: 565528 (The Pile)

Max Activating Token Index: 379

Text #9

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0664. Min Act: -0.0000

Data Index: 234798 (The Pile)

Max Activating Token Index: 874

Text #10

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0664. Min Act: -0.0000

Data Index: 438697 (The Pile)

Max Activating Token Index: 981

Text #11

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0662. Min Act: -0.0000

Data Index: 234434 (The Pile)

Max Activating Token Index: 404

Text #12

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0628. Min Act: -0.0000

Data Index: 1882608 (The Pile)

Max Activating Token Index: 291

Text #13

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0658. Min Act: -0.0000

Data Index: 238740 (The Pile)

Max Activating Token Index: 132

Text #14

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0657. Min Act: -0.0000

Data Index: 537080 (The Pile)

Max Activating Token Index: 128

Text #15

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0652. Min Act: -0.0000

Data Index: 1604690 (The Pile)

Max Activating Token Index: 892

Text #16

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0607. Min Act: -0.0000

Data Index: 849593 (The Pile)

Max Activating Token Index: 872

Text #17

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0648. Min Act: -0.0000

Data Index: 1553495 (The Pile)

Max Activating Token Index: 413

Text #18

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0595. Min Act: -0.0000

Data Index: 882945 (The Pile)

Max Activating Token Index: 61

Text #19

Max Range: 0.1060. Min Range: -0.1060

Max Act: 0.0625. Min Act: -0.0000

Data Index: 1832017 (The Pile)

Max Activating Token Index: 212