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

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

Neuron 3152 in Layer 6

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: 0.2697. Min Act: -0.0001

Data Index: 1063039 (C4 (Web Text))

Max Activating Token Index: 661

Text #1

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2505. Min Act: -0.0001

Data Index: 664631 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2447. Min Act: -0.0001

Data Index: 1201908 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2356. Min Act: -0.0001

Data Index: 1315341 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.2293. Min Act: -0.0001

Data Index: 656676 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1968. Min Act: -0.0001

Data Index: 1243017 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1924. Min Act: -0.0001

Data Index: 1023268 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1935. Min Act: -0.0000

Data Index: 1205923 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1900. Min Act: -0.0001

Data Index: 183445 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1841. Min Act: -0.0001

Data Index: 1049676 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1906. Min Act: -0.0000

Data Index: 1216551 (C4 (Web Text))

Max Activating Token Index: 989

Text #11

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1768. Min Act: -0.0001

Data Index: 488566 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1810. Min Act: -0.0000

Data Index: 657625 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1708. Min Act: -0.0000

Data Index: 234105 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1743. Min Act: -0.0000

Data Index: 163429 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1747. Min Act: -0.0001

Data Index: 550568 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1730. Min Act: -0.0000

Data Index: 334126 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1727. Min Act: -0.0000

Data Index: 344405 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1718. Min Act: -0.0000

Data Index: 1159413 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 0.2697. Min Range: -0.2697

Max Act: 0.1712. Min Act: -0.0001

Data Index: 446814 (C4 (Web Text))

Max Activating Token Index: 245