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

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

Neuron 2560 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1707. Min Range: -0.1707

Max Act: 0.1707. Min Act: -0.0002

Data Index: 1240743 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 0.1707. Min Range: -0.1707

Max Act: 0.1437. Min Act: -0.0002

Data Index: 1250843 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 0.1707. Min Range: -0.1707

Max Act: 0.1078. Min Act: -0.0002

Data Index: 47922 (C4 (Web Text))

Max Activating Token Index: 293

Text #3

Max Range: 0.1707. Min Range: -0.1707

Max Act: 0.1145. Min Act: -0.0002

Data Index: 412270 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 0.1707. Min Range: -0.1707

Max Act: 0.1034. Min Act: -0.0002

Data Index: 327905 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 0.1707. Min Range: -0.1707

Max Act: 0.1037. Min Act: -0.0002

Data Index: 956243 (C4 (Web Text))

Max Activating Token Index: 586

Text #6

Max Range: 0.1707. Min Range: -0.1707

Max Act: 0.0915. Min Act: -0.0002

Data Index: 128701 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 0.1707. Min Range: -0.1707

Max Act: 0.0934. Min Act: -0.0002

Data Index: 871682 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 0.1707. Min Range: -0.1707

Max Act: 0.0928. Min Act: -0.0002

Data Index: 412040 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 0.1707. Min Range: -0.1707

Max Act: 0.0969. Min Act: -0.0002

Data Index: 171972 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 0.1707. Min Range: -0.1707

Max Act: 0.0934. Min Act: -0.0002

Data Index: 1143854 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 0.1707. Min Range: -0.1707

Max Act: 0.0932. Min Act: -0.0002

Data Index: 247022 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 0.1707. Min Range: -0.1707

Max Act: 0.0902. Min Act: -0.0002

Data Index: 627593 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 0.1707. Min Range: -0.1707

Max Act: 0.0880. Min Act: -0.0002

Data Index: 76835 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 0.1707. Min Range: -0.1707

Max Act: 0.0820. Min Act: -0.0002

Data Index: 1177596 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 0.1707. Min Range: -0.1707

Max Act: 0.0830. Min Act: -0.0002

Data Index: 1085692 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 0.1707. Min Range: -0.1707

Max Act: 0.0859. Min Act: -0.0002

Data Index: 925470 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 0.1707. Min Range: -0.1707

Max Act: 0.0813. Min Act: -0.0002

Data Index: 922184 (C4 (Web Text))

Max Activating Token Index: 802

Text #18

Max Range: 0.1707. Min Range: -0.1707

Max Act: 0.0809. Min Act: -0.0002

Data Index: 933172 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 0.1707. Min Range: -0.1707

Max Act: 0.0806. Min Act: -0.0002

Data Index: 710078 (C4 (Web Text))

Max Activating Token Index: 598