Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1608 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0954. Min Act: -0.0003

Data Index: 314952 (C4 (Web Text))

Max Activating Token Index: 615

Text #1

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0856. Min Act: -0.0003

Data Index: 639305 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0831. Min Act: -0.0003

Data Index: 597424 (C4 (Web Text))

Max Activating Token Index: 456

Text #3

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0834. Min Act: -0.0003

Data Index: 453240 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0776. Min Act: -0.0004

Data Index: 10386 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0800. Min Act: -0.0004

Data Index: 1012383 (C4 (Web Text))

Max Activating Token Index: 403

Text #6

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0770. Min Act: -0.0003

Data Index: 457935 (C4 (Web Text))

Max Activating Token Index: 819

Text #7

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0809. Min Act: -0.0003

Data Index: 98525 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0787. Min Act: -0.0003

Data Index: 77931 (C4 (Web Text))

Max Activating Token Index: 232

Text #9

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0736. Min Act: -0.0003

Data Index: 487898 (C4 (Web Text))

Max Activating Token Index: 451

Text #10

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0734. Min Act: -0.0003

Data Index: 950749 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0703. Min Act: -0.0003

Data Index: 660733 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0709. Min Act: -0.0003

Data Index: 509591 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0672. Min Act: -0.0003

Data Index: 37827 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0718. Min Act: -0.0003

Data Index: 195733 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0687. Min Act: -0.0004

Data Index: 1301164 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0703. Min Act: -0.0004

Data Index: 615391 (C4 (Web Text))

Max Activating Token Index: 537

Text #17

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0737. Min Act: -0.0003

Data Index: 472908 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0677. Min Act: -0.0003

Data Index: 998001 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 0.0954. Min Range: -0.0954

Max Act: 0.0673. Min Act: -0.0003

Data Index: 1280757 (C4 (Web Text))

Max Activating Token Index: 489