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

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

Neuron 715 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: 0.0854. Min Range: -0.0854

Max Act: 0.0854. Min Act: -0.0002

Data Index: 514739 (C4 (Web Text))

Max Activating Token Index: 607

Text #1

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0772. Min Act: -0.0002

Data Index: 993444 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0759. Min Act: -0.0001

Data Index: 1257864 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0740. Min Act: -0.0002

Data Index: 807454 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0742. Min Act: -0.0002

Data Index: 957317 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0694. Min Act: -0.0001

Data Index: 768608 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0711. Min Act: -0.0002

Data Index: 1066077 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0710. Min Act: -0.0002

Data Index: 224256 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0681. Min Act: -0.0001

Data Index: 388662 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0686. Min Act: -0.0002

Data Index: 561152 (C4 (Web Text))

Max Activating Token Index: 806

Text #10

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0688. Min Act: -0.0002

Data Index: 1139570 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0699. Min Act: -0.0002

Data Index: 1075584 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0699. Min Act: -0.0002

Data Index: 483252 (C4 (Web Text))

Max Activating Token Index: 747

Text #13

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0685. Min Act: 0.0001

Data Index: 57258 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0680. Min Act: -0.0001

Data Index: 1246755 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0667. Min Act: -0.0002

Data Index: 306813 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0690. Min Act: 0.0002

Data Index: 612390 (C4 (Web Text))

Max Activating Token Index: 985

Text #17

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0676. Min Act: -0.0002

Data Index: 34554 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0654. Min Act: -0.0001

Data Index: 1335471 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0675. Min Act: -0.0002

Data Index: 862039 (C4 (Web Text))

Max Activating Token Index: 361