Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2749 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0911. Min Act: -0.0002

Data Index: 948036 (C4 (Web Text))

Max Activating Token Index: 726

Text #1

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0918. Min Act: -0.0002

Data Index: 330675 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0918. Min Act: -0.0002

Data Index: 850954 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0903. Min Act: -0.0002

Data Index: 1033801 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0883. Min Act: -0.0002

Data Index: 846632 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0866. Min Act: -0.0002

Data Index: 585480 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0864. Min Act: -0.0002

Data Index: 722997 (C4 (Web Text))

Max Activating Token Index: 504

Text #7

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0858. Min Act: -0.0002

Data Index: 1278255 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0875. Min Act: -0.0002

Data Index: 700120 (C4 (Web Text))

Max Activating Token Index: 203

Text #9

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0864. Min Act: -0.0002

Data Index: 812842 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0858. Min Act: -0.0002

Data Index: 472922 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0848. Min Act: -0.0002

Data Index: 152946 (C4 (Web Text))

Max Activating Token Index: 504

Text #12

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0857. Min Act: -0.0002

Data Index: 991153 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0830. Min Act: -0.0002

Data Index: 714018 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0847. Min Act: -0.0002

Data Index: 193160 (C4 (Web Text))

Max Activating Token Index: 542

Text #15

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0849. Min Act: -0.0002

Data Index: 158869 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0850. Min Act: -0.0002

Data Index: 1186874 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0843. Min Act: -0.0002

Data Index: 1514335 (Python Code)

Max Activating Token Index: 2

Text #18

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0840. Min Act: -0.0002

Data Index: 183603 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0828. Min Act: -0.0002

Data Index: 255672 (C4 (Web Text))

Max Activating Token Index: 471