Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 948 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0863. Min Act: -0.0001

Data Index: 943501 (C4 (Web Text))

Max Activating Token Index: 430

Text #1

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0819. Min Act: -0.0002

Data Index: 750824 (C4 (Web Text))

Max Activating Token Index: 278

Text #2

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0757. Min Act: -0.0002

Data Index: 1216359 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0779. Min Act: -0.0001

Data Index: 860826 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0776. Min Act: -0.0001

Data Index: 781236 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0779. Min Act: -0.0001

Data Index: 672122 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0709. Min Act: -0.0001

Data Index: 1079065 (C4 (Web Text))

Max Activating Token Index: 173

Text #7

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0736. Min Act: -0.0001

Data Index: 1246741 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0716. Min Act: -0.0002

Data Index: 907692 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0716. Min Act: -0.0001

Data Index: 883510 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0735. Min Act: -0.0002

Data Index: 203547 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0714. Min Act: -0.0002

Data Index: 941577 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0738. Min Act: -0.0001

Data Index: 1263789 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0681. Min Act: -0.0001

Data Index: 1181956 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0731. Min Act: -0.0002

Data Index: 326580 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0710. Min Act: -0.0001

Data Index: 1165348 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0731. Min Act: -0.0002

Data Index: 621019 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0653. Min Act: -0.0002

Data Index: 1237822 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0756. Min Act: -0.0002

Data Index: 1296455 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0717. Min Act: -0.0002

Data Index: 543424 (C4 (Web Text))

Max Activating Token Index: 195