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

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

Neuron 355 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2593. Min Act: -0.0001

Data Index: 830487 (C4 (Web Text))

Max Activating Token Index: 503

Text #1

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2697. Min Act: -0.0000

Data Index: 682386 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2322. Min Act: -0.0001

Data Index: 281020 (C4 (Web Text))

Max Activating Token Index: 697

Text #3

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2235. Min Act: -0.0001

Data Index: 782057 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2316. Min Act: -0.0001

Data Index: 230506 (C4 (Web Text))

Max Activating Token Index: 601

Text #5

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2068. Min Act: -0.0000

Data Index: 247920 (C4 (Web Text))

Max Activating Token Index: 865

Text #6

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2066. Min Act: -0.0001

Data Index: 214792 (C4 (Web Text))

Max Activating Token Index: 518

Text #7

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1941. Min Act: -0.0001

Data Index: 1310568 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1975. Min Act: -0.0001

Data Index: 1024457 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1972. Min Act: -0.0000

Data Index: 795865 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1872. Min Act: -0.0000

Data Index: 53046 (C4 (Web Text))

Max Activating Token Index: 983

Text #11

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1860. Min Act: -0.0001

Data Index: 1040130 (C4 (Web Text))

Max Activating Token Index: 378

Text #12

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1863. Min Act: -0.0001

Data Index: 201832 (C4 (Web Text))

Max Activating Token Index: 734

Text #13

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1846. Min Act: -0.0000

Data Index: 372266 (C4 (Web Text))

Max Activating Token Index: 512

Text #14

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1946. Min Act: -0.0000

Data Index: 154778 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1798. Min Act: -0.0001

Data Index: 248659 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1890. Min Act: -0.0001

Data Index: 459163 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1817. Min Act: -0.0000

Data Index: 935270 (C4 (Web Text))

Max Activating Token Index: 956

Text #18

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1735. Min Act: -0.0001

Data Index: 920241 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1792. Min Act: -0.0000

Data Index: 663385 (C4 (Web Text))

Max Activating Token Index: 290