Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2092 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1987. Min Act: -0.0001

Data Index: 1263373 (C4 (Web Text))

Max Activating Token Index: 354

Text #1

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1918. Min Act: -0.0001

Data Index: 1096417 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1882. Min Act: -0.0001

Data Index: 38631 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1803. Min Act: -0.0001

Data Index: 396489 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1854. Min Act: -0.0001

Data Index: 847102 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1818. Min Act: -0.0001

Data Index: 1177999 (C4 (Web Text))

Max Activating Token Index: 220

Text #6

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1718. Min Act: -0.0001

Data Index: 113293 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1727. Min Act: -0.0001

Data Index: 151374 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1730. Min Act: -0.0001

Data Index: 156132 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1709. Min Act: -0.0001

Data Index: 1221856 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1741. Min Act: -0.0001

Data Index: 540696 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1716. Min Act: -0.0001

Data Index: 806341 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1662. Min Act: -0.0001

Data Index: 989609 (C4 (Web Text))

Max Activating Token Index: 91

Text #13

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1598. Min Act: -0.0001

Data Index: 1216362 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1660. Min Act: -0.0001

Data Index: 277302 (C4 (Web Text))

Max Activating Token Index: 572

Text #15

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1533. Min Act: -0.0001

Data Index: 551833 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1517. Min Act: -0.0001

Data Index: 1265582 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1488. Min Act: -0.0001

Data Index: 253633 (C4 (Web Text))

Max Activating Token Index: 81

Text #18

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1595. Min Act: -0.0001

Data Index: 449729 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1533. Min Act: -0.0001

Data Index: 1046933 (C4 (Web Text))

Max Activating Token Index: 89