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

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

Neuron 734 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7224. Min Range: -1.7224

Max Act: 1.7224. Min Act: -0.0000

Data Index: 18484 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 1.7224. Min Range: -1.7224

Max Act: 1.6651. Min Act: -0.0000

Data Index: 706760 (C4 (Web Text))

Max Activating Token Index: 392

Text #2

Max Range: 1.7224. Min Range: -1.7224

Max Act: 1.4900. Min Act: -0.0000

Data Index: 508623 (C4 (Web Text))

Max Activating Token Index: 317

Text #3

Max Range: 1.7224. Min Range: -1.7224

Max Act: 1.3709. Min Act: -0.0000

Data Index: 1067170 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 1.7224. Min Range: -1.7224

Max Act: 1.4686. Min Act: -0.0000

Data Index: 747649 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 1.7224. Min Range: -1.7224

Max Act: 1.2866. Min Act: -0.0000

Data Index: 1085090 (C4 (Web Text))

Max Activating Token Index: 506

Text #6

Max Range: 1.7224. Min Range: -1.7224

Max Act: 1.3572. Min Act: -0.0000

Data Index: 27159 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 1.7224. Min Range: -1.7224

Max Act: 1.2650. Min Act: -0.0000

Data Index: 351836 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 1.7224. Min Range: -1.7224

Max Act: 1.2659. Min Act: -0.0000

Data Index: 1151355 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 1.7224. Min Range: -1.7224

Max Act: 1.2109. Min Act: -0.0000

Data Index: 120083 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 1.7224. Min Range: -1.7224

Max Act: 1.1753. Min Act: -0.0000

Data Index: 482736 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 1.7224. Min Range: -1.7224

Max Act: 1.2640. Min Act: -0.0000

Data Index: 912920 (C4 (Web Text))

Max Activating Token Index: 377

Text #12

Max Range: 1.7224. Min Range: -1.7224

Max Act: 1.1770. Min Act: -0.0000

Data Index: 52495 (C4 (Web Text))

Max Activating Token Index: 646

Text #13

Max Range: 1.7224. Min Range: -1.7224

Max Act: 1.0461. Min Act: -0.0000

Data Index: 49065 (C4 (Web Text))

Max Activating Token Index: 876

Text #14

Max Range: 1.7224. Min Range: -1.7224

Max Act: 1.1476. Min Act: -0.0000

Data Index: 442719 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 1.7224. Min Range: -1.7224

Max Act: 1.0823. Min Act: -0.0000

Data Index: 109926 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 1.7224. Min Range: -1.7224

Max Act: 1.1487. Min Act: -0.0000

Data Index: 905955 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 1.7224. Min Range: -1.7224

Max Act: 1.0782. Min Act: -0.0000

Data Index: 10168 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 1.7224. Min Range: -1.7224

Max Act: 1.1195. Min Act: -0.0000

Data Index: 961511 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 1.7224. Min Range: -1.7224

Max Act: 1.0604. Min Act: -0.0000

Data Index: 66646 (C4 (Web Text))

Max Activating Token Index: 716