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

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

Neuron 1313 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: 0.0939. Min Range: -0.0939

Max Act: 0.0939. Min Act: -0.0002

Data Index: 175664 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0908. Min Act: -0.0002

Data Index: 748394 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0857. Min Act: -0.0002

Data Index: 895447 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0850. Min Act: -0.0002

Data Index: 747306 (C4 (Web Text))

Max Activating Token Index: 601

Text #4

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0845. Min Act: -0.0002

Data Index: 955373 (C4 (Web Text))

Max Activating Token Index: 471

Text #5

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0825. Min Act: -0.0002

Data Index: 307879 (C4 (Web Text))

Max Activating Token Index: 714

Text #6

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0823. Min Act: -0.0002

Data Index: 13332 (C4 (Web Text))

Max Activating Token Index: 365

Text #7

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0825. Min Act: -0.0002

Data Index: 994693 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0820. Min Act: -0.0002

Data Index: 1016 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0799. Min Act: -0.0002

Data Index: 101918 (C4 (Web Text))

Max Activating Token Index: 145

Text #10

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0803. Min Act: -0.0002

Data Index: 540226 (C4 (Web Text))

Max Activating Token Index: 135

Text #11

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0793. Min Act: -0.0002

Data Index: 1143535 (C4 (Web Text))

Max Activating Token Index: 723

Text #12

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0799. Min Act: -0.0002

Data Index: 75850 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0777. Min Act: -0.0002

Data Index: 695843 (C4 (Web Text))

Max Activating Token Index: 980

Text #14

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0782. Min Act: -0.0002

Data Index: 440848 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0776. Min Act: -0.0002

Data Index: 864041 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0771. Min Act: -0.0002

Data Index: 1160446 (C4 (Web Text))

Max Activating Token Index: 385

Text #17

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0780. Min Act: -0.0002

Data Index: 691156 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0779. Min Act: -0.0002

Data Index: 1098842 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0776. Min Act: -0.0002

Data Index: 391898 (C4 (Web Text))

Max Activating Token Index: 581