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

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

Neuron 3456 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: 0.1496. Min Range: -0.1496

Max Act: 0.1496. Min Act: -0.0001

Data Index: 1592381 (Python Code)

Max Activating Token Index: 375

Text #1

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1341. Min Act: -0.0001

Data Index: 1404078 (Python Code)

Max Activating Token Index: 660

Text #2

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1111. Min Act: -0.0001

Data Index: 1591130 (Python Code)

Max Activating Token Index: 277

Text #3

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1143. Min Act: -0.0001

Data Index: 1503473 (Python Code)

Max Activating Token Index: 664

Text #4

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1016. Min Act: -0.0000

Data Index: 1534917 (Python Code)

Max Activating Token Index: 673

Text #5

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1048. Min Act: -0.0001

Data Index: 1443776 (Python Code)

Max Activating Token Index: 214

Text #6

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.0981. Min Act: -0.0001

Data Index: 1458967 (Python Code)

Max Activating Token Index: 404

Text #7

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.0941. Min Act: -0.0001

Data Index: 1415943 (Python Code)

Max Activating Token Index: 586

Text #8

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1001. Min Act: -0.0001

Data Index: 1637065 (Python Code)

Max Activating Token Index: 123

Text #9

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.1030. Min Act: -0.0001

Data Index: 907790 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.0977. Min Act: -0.0001

Data Index: 1431184 (Python Code)

Max Activating Token Index: 368

Text #11

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.0895. Min Act: -0.0001

Data Index: 1439179 (Python Code)

Max Activating Token Index: 825

Text #12

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.0901. Min Act: -0.0001

Data Index: 1530708 (Python Code)

Max Activating Token Index: 563

Text #13

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.0866. Min Act: -0.0001

Data Index: 1518195 (Python Code)

Max Activating Token Index: 870

Text #14

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.0932. Min Act: -0.0001

Data Index: 1623696 (Python Code)

Max Activating Token Index: 401

Text #15

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.0959. Min Act: -0.0001

Data Index: 1543719 (Python Code)

Max Activating Token Index: 83

Text #16

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.0895. Min Act: -0.0001

Data Index: 1591923 (Python Code)

Max Activating Token Index: 109

Text #17

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.0922. Min Act: -0.0000

Data Index: 897821 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.0897. Min Act: -0.0001

Data Index: 1645642 (Python Code)

Max Activating Token Index: 163

Text #19

Max Range: 0.1496. Min Range: -0.1496

Max Act: 0.0953. Min Act: -0.0001

Data Index: 1507636 (Python Code)

Max Activating Token Index: 146