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

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

Neuron 2848 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6204. Min Range: -0.6204

Max Act: 0.6204. Min Act: -0.0001

Data Index: 1297232 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 0.6204. Min Range: -0.6204

Max Act: 0.6090. Min Act: -0.0001

Data Index: 1267137 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 0.6204. Min Range: -0.6204

Max Act: 0.5792. Min Act: -0.0001

Data Index: 786155 (C4 (Web Text))

Max Activating Token Index: 627

Text #3

Max Range: 0.6204. Min Range: -0.6204

Max Act: 0.5648. Min Act: -0.0002

Data Index: 544164 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 0.6204. Min Range: -0.6204

Max Act: 0.5454. Min Act: -0.0002

Data Index: 147875 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 0.6204. Min Range: -0.6204

Max Act: 0.5611. Min Act: -0.0001

Data Index: 944785 (C4 (Web Text))

Max Activating Token Index: 709

Text #6

Max Range: 0.6204. Min Range: -0.6204

Max Act: 0.5533. Min Act: -0.0002

Data Index: 874529 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 0.6204. Min Range: -0.6204

Max Act: 0.5068. Min Act: -0.0002

Data Index: 184013 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 0.6204. Min Range: -0.6204

Max Act: 0.5044. Min Act: -0.0002

Data Index: 833160 (C4 (Web Text))

Max Activating Token Index: 173

Text #9

Max Range: 0.6204. Min Range: -0.6204

Max Act: 0.5113. Min Act: -0.0002

Data Index: 453109 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 0.6204. Min Range: -0.6204

Max Act: 0.5317. Min Act: -0.0001

Data Index: 353895 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 0.6204. Min Range: -0.6204

Max Act: 0.4850. Min Act: -0.0001

Data Index: 784125 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 0.6204. Min Range: -0.6204

Max Act: 0.5096. Min Act: -0.0002

Data Index: 598646 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 0.6204. Min Range: -0.6204

Max Act: 0.5030. Min Act: -0.0002

Data Index: 794690 (C4 (Web Text))

Max Activating Token Index: 1003

Text #14

Max Range: 0.6204. Min Range: -0.6204

Max Act: 0.4673. Min Act: -0.0002

Data Index: 154504 (C4 (Web Text))

Max Activating Token Index: 1019

Text #15

Max Range: 0.6204. Min Range: -0.6204

Max Act: 0.4982. Min Act: -0.0002

Data Index: 728983 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 0.6204. Min Range: -0.6204

Max Act: 0.4754. Min Act: -0.0001

Data Index: 755763 (C4 (Web Text))

Max Activating Token Index: 741

Text #17

Max Range: 0.6204. Min Range: -0.6204

Max Act: 0.4770. Min Act: -0.0002

Data Index: 146082 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 0.6204. Min Range: -0.6204

Max Act: 0.4766. Min Act: -0.0001

Data Index: 176337 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 0.6204. Min Range: -0.6204

Max Act: 0.4845. Min Act: -0.0002

Data Index: 17819 (C4 (Web Text))

Max Activating Token Index: 306