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

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

Neuron 2518 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.1012. Min Act: -0.0000

Data Index: 769629 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0961. Min Act: -0.0000

Data Index: 480699 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.1005. Min Act: -0.0000

Data Index: 85541 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.1003. Min Act: -0.0000

Data Index: 910156 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.1000. Min Act: -0.0000

Data Index: 157504 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0954. Min Act: -0.0000

Data Index: 1229031 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0904. Min Act: -0.0000

Data Index: 303785 (C4 (Web Text))

Max Activating Token Index: 1018

Text #7

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0841. Min Act: -0.0000

Data Index: 294289 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0810. Min Act: -0.0000

Data Index: 751361 (C4 (Web Text))

Max Activating Token Index: 461

Text #9

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0893. Min Act: -0.0000

Data Index: 402091 (C4 (Web Text))

Max Activating Token Index: 219

Text #10

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0873. Min Act: -0.0000

Data Index: 594814 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0893. Min Act: -0.0000

Data Index: 1132259 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0824. Min Act: -0.0000

Data Index: 278241 (C4 (Web Text))

Max Activating Token Index: 202

Text #13

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0855. Min Act: -0.0000

Data Index: 356774 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0804. Min Act: -0.0000

Data Index: 853262 (C4 (Web Text))

Max Activating Token Index: 554

Text #15

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0856. Min Act: -0.0000

Data Index: 1304223 (C4 (Web Text))

Max Activating Token Index: 126

Text #16

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0787. Min Act: -0.0000

Data Index: 680325 (C4 (Web Text))

Max Activating Token Index: 500

Text #17

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0754. Min Act: -0.0000

Data Index: 1193936 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0780. Min Act: -0.0000

Data Index: 581138 (C4 (Web Text))

Max Activating Token Index: 972

Text #19

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0795. Min Act: -0.0000

Data Index: 99366 (C4 (Web Text))

Max Activating Token Index: 378