Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1418 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5860. Min Range: -1.5860

Max Act: 1.5860. Min Act: -0.0001

Data Index: 124543 (C4 (Web Text))

Max Activating Token Index: 816

Text #1

Max Range: 1.5860. Min Range: -1.5860

Max Act: 1.5368. Min Act: -0.0001

Data Index: 457061 (C4 (Web Text))

Max Activating Token Index: 817

Text #2

Max Range: 1.5860. Min Range: -1.5860

Max Act: 1.5643. Min Act: -0.0001

Data Index: 49151 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 1.5860. Min Range: -1.5860

Max Act: 1.4861. Min Act: -0.0001

Data Index: 464903 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 1.5860. Min Range: -1.5860

Max Act: 1.4703. Min Act: -0.0001

Data Index: 981137 (C4 (Web Text))

Max Activating Token Index: 535

Text #5

Max Range: 1.5860. Min Range: -1.5860

Max Act: 1.4316. Min Act: -0.0001

Data Index: 433970 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 1.5860. Min Range: -1.5860

Max Act: 1.4162. Min Act: -0.0001

Data Index: 337547 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 1.5860. Min Range: -1.5860

Max Act: 1.3400. Min Act: -0.0001

Data Index: 153029 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 1.5860. Min Range: -1.5860

Max Act: 1.2924. Min Act: -0.0001

Data Index: 1198869 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 1.5860. Min Range: -1.5860

Max Act: 1.4067. Min Act: -0.0001

Data Index: 360743 (C4 (Web Text))

Max Activating Token Index: 990

Text #10

Max Range: 1.5860. Min Range: -1.5860

Max Act: 1.2951. Min Act: -0.0001

Data Index: 653811 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 1.5860. Min Range: -1.5860

Max Act: 1.3074. Min Act: -0.0001

Data Index: 641874 (C4 (Web Text))

Max Activating Token Index: 979

Text #12

Max Range: 1.5860. Min Range: -1.5860

Max Act: 1.2932. Min Act: -0.0001

Data Index: 1262270 (C4 (Web Text))

Max Activating Token Index: 479

Text #13

Max Range: 1.5860. Min Range: -1.5860

Max Act: 1.1275. Min Act: -0.0001

Data Index: 532057 (C4 (Web Text))

Max Activating Token Index: 691

Text #14

Max Range: 1.5860. Min Range: -1.5860

Max Act: 1.2456. Min Act: -0.0001

Data Index: 1189849 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 1.5860. Min Range: -1.5860

Max Act: 1.3197. Min Act: -0.0001

Data Index: 1069667 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 1.5860. Min Range: -1.5860

Max Act: 1.2706. Min Act: -0.0001

Data Index: 1202052 (C4 (Web Text))

Max Activating Token Index: 273

Text #17

Max Range: 1.5860. Min Range: -1.5860

Max Act: 1.2720. Min Act: -0.0001

Data Index: 1215404 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 1.5860. Min Range: -1.5860

Max Act: 1.1919. Min Act: -0.0001

Data Index: 309756 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 1.5860. Min Range: -1.5860

Max Act: 1.3199. Min Act: -0.0001

Data Index: 15330 (C4 (Web Text))

Max Activating Token Index: 191