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

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

Neuron 3585 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.2103. Min Act: -0.0003

Data Index: 390762 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1883. Min Act: -0.0003

Data Index: 149252 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1898. Min Act: -0.0003

Data Index: 78096 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1931. Min Act: -0.0002

Data Index: 97339 (C4 (Web Text))

Max Activating Token Index: 585

Text #4

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1849. Min Act: -0.0003

Data Index: 279451 (C4 (Web Text))

Max Activating Token Index: 640

Text #5

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1848. Min Act: -0.0002

Data Index: 363345 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1818. Min Act: -0.0003

Data Index: 1141660 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1738. Min Act: -0.0003

Data Index: 344824 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1731. Min Act: -0.0003

Data Index: 143642 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1712. Min Act: -0.0002

Data Index: 1095403 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1694. Min Act: -0.0002

Data Index: 1304591 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1736. Min Act: -0.0003

Data Index: 1305917 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1702. Min Act: -0.0003

Data Index: 695011 (C4 (Web Text))

Max Activating Token Index: 949

Text #13

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1617. Min Act: -0.0003

Data Index: 615752 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1530. Min Act: -0.0002

Data Index: 1307817 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1459. Min Act: -0.0002

Data Index: 251449 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1558. Min Act: -0.0002

Data Index: 785101 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1475. Min Act: -0.0002

Data Index: 1169900 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1464. Min Act: -0.0002

Data Index: 241548 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1410. Min Act: -0.0003

Data Index: 262792 (C4 (Web Text))

Max Activating Token Index: 523