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

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

Neuron 1939 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: 3.0876. Min Range: -3.0876

Max Act: 2.9867. Min Act: -0.0001

Data Index: 692936 (C4 (Web Text))

Max Activating Token Index: 321

Text #1

Max Range: 3.0876. Min Range: -3.0876

Max Act: 3.0876. Min Act: -0.0001

Data Index: 986575 (C4 (Web Text))

Max Activating Token Index: 176

Text #2

Max Range: 3.0876. Min Range: -3.0876

Max Act: 3.0671. Min Act: -0.0002

Data Index: 391083 (C4 (Web Text))

Max Activating Token Index: 151

Text #3

Max Range: 3.0876. Min Range: -3.0876

Max Act: 2.7580. Min Act: -0.0001

Data Index: 389772 (C4 (Web Text))

Max Activating Token Index: 694

Text #4

Max Range: 3.0876. Min Range: -3.0876

Max Act: 2.7719. Min Act: -0.0001

Data Index: 866474 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 3.0876. Min Range: -3.0876

Max Act: 2.7354. Min Act: -0.0001

Data Index: 1227158 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 3.0876. Min Range: -3.0876

Max Act: 2.8102. Min Act: -0.0001

Data Index: 1125598 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 3.0876. Min Range: -3.0876

Max Act: 2.6136. Min Act: -0.0001

Data Index: 1198300 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 3.0876. Min Range: -3.0876

Max Act: 2.0711. Min Act: -0.0001

Data Index: 379310 (C4 (Web Text))

Max Activating Token Index: 733

Text #9

Max Range: 3.0876. Min Range: -3.0876

Max Act: 2.3560. Min Act: -0.0001

Data Index: 1381825 (Python Code)

Max Activating Token Index: 55

Text #10

Max Range: 3.0876. Min Range: -3.0876

Max Act: 2.1208. Min Act: -0.0002

Data Index: 1262430 (C4 (Web Text))

Max Activating Token Index: 683

Text #11

Max Range: 3.0876. Min Range: -3.0876

Max Act: 2.0964. Min Act: -0.0002

Data Index: 1251120 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 3.0876. Min Range: -3.0876

Max Act: 2.0716. Min Act: -0.0002

Data Index: 908255 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 3.0876. Min Range: -3.0876

Max Act: 2.1868. Min Act: -0.0001

Data Index: 1368583 (Python Code)

Max Activating Token Index: 928

Text #14

Max Range: 3.0876. Min Range: -3.0876

Max Act: 1.8461. Min Act: -0.0001

Data Index: 1061134 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 3.0876. Min Range: -3.0876

Max Act: 2.0528. Min Act: -0.0001

Data Index: 315894 (C4 (Web Text))

Max Activating Token Index: 234

Text #16

Max Range: 3.0876. Min Range: -3.0876

Max Act: 2.1677. Min Act: -0.0001

Data Index: 245344 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 3.0876. Min Range: -3.0876

Max Act: 2.0621. Min Act: -0.0001

Data Index: 386962 (C4 (Web Text))

Max Activating Token Index: 211

Text #18

Max Range: 3.0876. Min Range: -3.0876

Max Act: 2.2724. Min Act: -0.0002

Data Index: 1327814 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 3.0876. Min Range: -3.0876

Max Act: 2.1516. Min Act: -0.0001

Data Index: 1416499 (Python Code)

Max Activating Token Index: 799