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

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

Neuron 399 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: 0.0920. Min Range: -0.0920

Max Act: 0.0783. Min Act: -0.0002

Data Index: 263012 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0920. Min Act: -0.0002

Data Index: 591681 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0865. Min Act: -0.0002

Data Index: 93269 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0896. Min Act: -0.0002

Data Index: 1187535 (C4 (Web Text))

Max Activating Token Index: 597

Text #4

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0744. Min Act: -0.0002

Data Index: 248851 (C4 (Web Text))

Max Activating Token Index: 514

Text #5

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0755. Min Act: -0.0002

Data Index: 789066 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0771. Min Act: -0.0002

Data Index: 844421 (C4 (Web Text))

Max Activating Token Index: 703

Text #7

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0762. Min Act: -0.0002

Data Index: 703170 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0877. Min Act: -0.0002

Data Index: 804598 (C4 (Web Text))

Max Activating Token Index: 337

Text #9

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0767. Min Act: -0.0002

Data Index: 953457 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0760. Min Act: -0.0002

Data Index: 843010 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0753. Min Act: -0.0002

Data Index: 938476 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0726. Min Act: -0.0002

Data Index: 785499 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0825. Min Act: -0.0002

Data Index: 465247 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0768. Min Act: -0.0002

Data Index: 73891 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0817. Min Act: -0.0002

Data Index: 864002 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0787. Min Act: -0.0002

Data Index: 245585 (C4 (Web Text))

Max Activating Token Index: 524

Text #17

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0736. Min Act: -0.0002

Data Index: 1000850 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0697. Min Act: -0.0002

Data Index: 20222 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0695. Min Act: -0.0002

Data Index: 1019062 (C4 (Web Text))

Max Activating Token Index: 241