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

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

Neuron 2530 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: 1.8828. Min Range: -1.8828

Max Act: 1.8828. Min Act: -0.0001

Data Index: 225204 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 1.8828. Min Range: -1.8828

Max Act: 1.8207. Min Act: -0.0002

Data Index: 297114 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 1.8828. Min Range: -1.8828

Max Act: 1.7664. Min Act: -0.0002

Data Index: 67458 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 1.8828. Min Range: -1.8828

Max Act: 1.4872. Min Act: -0.0002

Data Index: 125070 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 1.8828. Min Range: -1.8828

Max Act: 1.3511. Min Act: -0.0002

Data Index: 1306602 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 1.8828. Min Range: -1.8828

Max Act: 1.3739. Min Act: -0.0001

Data Index: 485675 (C4 (Web Text))

Max Activating Token Index: 805

Text #6

Max Range: 1.8828. Min Range: -1.8828

Max Act: 1.3044. Min Act: -0.0002

Data Index: 259899 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 1.8828. Min Range: -1.8828

Max Act: 1.3207. Min Act: -0.0002

Data Index: 827356 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 1.8828. Min Range: -1.8828

Max Act: 1.1242. Min Act: -0.0002

Data Index: 95016 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 1.8828. Min Range: -1.8828

Max Act: 1.2855. Min Act: -0.0002

Data Index: 938071 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 1.8828. Min Range: -1.8828

Max Act: 1.1069. Min Act: -0.0001

Data Index: 963459 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 1.8828. Min Range: -1.8828

Max Act: 1.1711. Min Act: -0.0001

Data Index: 137764 (C4 (Web Text))

Max Activating Token Index: 809

Text #12

Max Range: 1.8828. Min Range: -1.8828

Max Act: 1.1075. Min Act: -0.0002

Data Index: 1321282 (C4 (Web Text))

Max Activating Token Index: 643

Text #13

Max Range: 1.8828. Min Range: -1.8828

Max Act: 1.0055. Min Act: -0.0002

Data Index: 349023 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 1.8828. Min Range: -1.8828

Max Act: 1.0623. Min Act: -0.0002

Data Index: 544173 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 1.8828. Min Range: -1.8828

Max Act: 0.9438. Min Act: -0.0002

Data Index: 1057798 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 1.8828. Min Range: -1.8828

Max Act: 0.8702. Min Act: -0.0001

Data Index: 36948 (C4 (Web Text))

Max Activating Token Index: 502

Text #17

Max Range: 1.8828. Min Range: -1.8828

Max Act: 0.8424. Min Act: -0.0001

Data Index: 565444 (C4 (Web Text))

Max Activating Token Index: 762

Text #18

Max Range: 1.8828. Min Range: -1.8828

Max Act: 1.0210. Min Act: -0.0002

Data Index: 39966 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 1.8828. Min Range: -1.8828

Max Act: 0.8882. Min Act: -0.0001

Data Index: 882184 (C4 (Web Text))

Max Activating Token Index: 912