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

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

Neuron 1256 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9706. Min Range: -4.9706

Max Act: 4.9706. Min Act: -0.0000

Data Index: 197905 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 4.9706. Min Range: -4.9706

Max Act: 4.2180. Min Act: -0.0000

Data Index: 1261492 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 4.9706. Min Range: -4.9706

Max Act: 3.9397. Min Act: -0.0000

Data Index: 960329 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 4.9706. Min Range: -4.9706

Max Act: 3.5674. Min Act: -0.0000

Data Index: 691643 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 4.9706. Min Range: -4.9706

Max Act: 3.5041. Min Act: -0.0000

Data Index: 199838 (C4 (Web Text))

Max Activating Token Index: 872

Text #5

Max Range: 4.9706. Min Range: -4.9706

Max Act: 3.3174. Min Act: -0.0000

Data Index: 1175577 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 4.9706. Min Range: -4.9706

Max Act: 3.4623. Min Act: -0.0000

Data Index: 118635 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 4.9706. Min Range: -4.9706

Max Act: 3.1501. Min Act: -0.0000

Data Index: 1087866 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 4.9706. Min Range: -4.9706

Max Act: 3.2762. Min Act: -0.0000

Data Index: 379430 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 4.9706. Min Range: -4.9706

Max Act: 3.1059. Min Act: -0.0000

Data Index: 381787 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 4.9706. Min Range: -4.9706

Max Act: 3.1191. Min Act: -0.0000

Data Index: 1034516 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 4.9706. Min Range: -4.9706

Max Act: 3.0704. Min Act: -0.0000

Data Index: 1324647 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 4.9706. Min Range: -4.9706

Max Act: 3.0649. Min Act: -0.0000

Data Index: 873592 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 4.9706. Min Range: -4.9706

Max Act: 3.1712. Min Act: -0.0000

Data Index: 893180 (C4 (Web Text))

Max Activating Token Index: 626

Text #14

Max Range: 4.9706. Min Range: -4.9706

Max Act: 2.8658. Min Act: -0.0000

Data Index: 1191836 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 4.9706. Min Range: -4.9706

Max Act: 3.1515. Min Act: -0.0000

Data Index: 122827 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 4.9706. Min Range: -4.9706

Max Act: 2.9128. Min Act: -0.0000

Data Index: 772899 (C4 (Web Text))

Max Activating Token Index: 259

Text #17

Max Range: 4.9706. Min Range: -4.9706

Max Act: 2.7613. Min Act: -0.0000

Data Index: 53184 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 4.9706. Min Range: -4.9706

Max Act: 2.7308. Min Act: -0.0000

Data Index: 81667 (C4 (Web Text))

Max Activating Token Index: 542

Text #19

Max Range: 4.9706. Min Range: -4.9706

Max Act: 2.8776. Min Act: -0.0000

Data Index: 200170 (C4 (Web Text))

Max Activating Token Index: 69