Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1637 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.1070. Min Act: -0.0002

Data Index: 897273 (C4 (Web Text))

Max Activating Token Index: 347

Text #1

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.1039. Min Act: -0.0002

Data Index: 67205 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.1062. Min Act: -0.0002

Data Index: 1294688 (C4 (Web Text))

Max Activating Token Index: 567

Text #3

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0931. Min Act: -0.0001

Data Index: 32204 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0860. Min Act: -0.0001

Data Index: 431888 (C4 (Web Text))

Max Activating Token Index: 553

Text #5

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0849. Min Act: -0.0002

Data Index: 11358 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0824. Min Act: -0.0001

Data Index: 536226 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0822. Min Act: -0.0002

Data Index: 1141099 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0853. Min Act: -0.0001

Data Index: 785174 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0825. Min Act: -0.0001

Data Index: 1243919 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0822. Min Act: -0.0002

Data Index: 969620 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0826. Min Act: -0.0002

Data Index: 720476 (C4 (Web Text))

Max Activating Token Index: 878

Text #12

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0832. Min Act: -0.0002

Data Index: 381869 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0798. Min Act: -0.0002

Data Index: 790360 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0813. Min Act: -0.0002

Data Index: 706793 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0798. Min Act: -0.0002

Data Index: 358992 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0807. Min Act: -0.0002

Data Index: 450443 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0771. Min Act: -0.0002

Data Index: 1161867 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0794. Min Act: -0.0002

Data Index: 542668 (C4 (Web Text))

Max Activating Token Index: 756

Text #19

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0767. Min Act: -0.0002

Data Index: 1809 (C4 (Web Text))

Max Activating Token Index: 748