Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1676 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0944. Min Act: -0.0002

Data Index: 852107 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0933. Min Act: -0.0002

Data Index: 751163 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0910. Min Act: -0.0002

Data Index: 545925 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0909. Min Act: -0.0002

Data Index: 1189288 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0895. Min Act: -0.0002

Data Index: 43428 (C4 (Web Text))

Max Activating Token Index: 535

Text #5

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0883. Min Act: -0.0002

Data Index: 359452 (C4 (Web Text))

Max Activating Token Index: 553

Text #6

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0868. Min Act: -0.0002

Data Index: 517939 (C4 (Web Text))

Max Activating Token Index: 684

Text #7

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0867. Min Act: -0.0002

Data Index: 176337 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0860. Min Act: -0.0002

Data Index: 1337244 (C4 (Web Text))

Max Activating Token Index: 304

Text #9

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0900. Min Act: -0.0002

Data Index: 221841 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0831. Min Act: -0.0001

Data Index: 1143337 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0828. Min Act: -0.0002

Data Index: 708933 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0859. Min Act: -0.0002

Data Index: 768533 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0850. Min Act: -0.0002

Data Index: 1091264 (C4 (Web Text))

Max Activating Token Index: 690

Text #14

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0801. Min Act: -0.0002

Data Index: 933609 (C4 (Web Text))

Max Activating Token Index: 775

Text #15

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0798. Min Act: -0.0000

Data Index: 450112 (C4 (Web Text))

Max Activating Token Index: 649

Text #16

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0813. Min Act: -0.0002

Data Index: 539376 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0824. Min Act: -0.0002

Data Index: 63701 (C4 (Web Text))

Max Activating Token Index: 221

Text #18

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0813. Min Act: -0.0002

Data Index: 1196224 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0821. Min Act: -0.0002

Data Index: 650744 (C4 (Web Text))

Max Activating Token Index: 971