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

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

Neuron 4258 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: 0.1009. Min Range: -0.1009

Max Act: 0.0948. Min Act: -0.0002

Data Index: 1067140 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0929. Min Act: -0.0002

Data Index: 1090324 (C4 (Web Text))

Max Activating Token Index: 513

Text #2

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0866. Min Act: -0.0002

Data Index: 671855 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0921. Min Act: -0.0002

Data Index: 790859 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.1009. Min Act: -0.0002

Data Index: 620485 (C4 (Web Text))

Max Activating Token Index: 242

Text #5

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0894. Min Act: -0.0002

Data Index: 21669 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0910. Min Act: -0.0002

Data Index: 254235 (C4 (Web Text))

Max Activating Token Index: 924

Text #7

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0875. Min Act: -0.0002

Data Index: 281059 (C4 (Web Text))

Max Activating Token Index: 625

Text #8

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0986. Min Act: -0.0002

Data Index: 255512 (C4 (Web Text))

Max Activating Token Index: 718

Text #9

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0770. Min Act: -0.0002

Data Index: 1101385 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0783. Min Act: -0.0002

Data Index: 92305 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0845. Min Act: -0.0002

Data Index: 872052 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0938. Min Act: -0.0002

Data Index: 643300 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0709. Min Act: -0.0002

Data Index: 626965 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0849. Min Act: -0.0002

Data Index: 935411 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0816. Min Act: -0.0002

Data Index: 138363 (C4 (Web Text))

Max Activating Token Index: 582

Text #16

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0866. Min Act: -0.0002

Data Index: 902305 (C4 (Web Text))

Max Activating Token Index: 379

Text #17

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0835. Min Act: -0.0002

Data Index: 860757 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0835. Min Act: -0.0002

Data Index: 139841 (C4 (Web Text))

Max Activating Token Index: 198

Text #19

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0859. Min Act: -0.0002

Data Index: 1202563 (C4 (Web Text))

Max Activating Token Index: 260