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

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

Neuron 3405 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4787. Min Range: -2.4787

Max Act: 2.3742. Min Act: -0.0000

Data Index: 5843 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 2.4787. Min Range: -2.4787

Max Act: 2.4787. Min Act: -0.0000

Data Index: 430689 (C4 (Web Text))

Max Activating Token Index: 284

Text #2

Max Range: 2.4787. Min Range: -2.4787

Max Act: 2.2707. Min Act: -0.0000

Data Index: 220877 (C4 (Web Text))

Max Activating Token Index: 839

Text #3

Max Range: 2.4787. Min Range: -2.4787

Max Act: 2.1294. Min Act: -0.0000

Data Index: 595838 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 2.4787. Min Range: -2.4787

Max Act: 2.2309. Min Act: -0.0000

Data Index: 620003 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 2.4787. Min Range: -2.4787

Max Act: 2.1025. Min Act: -0.0000

Data Index: 963476 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 2.4787. Min Range: -2.4787

Max Act: 2.2276. Min Act: -0.0000

Data Index: 256837 (C4 (Web Text))

Max Activating Token Index: 468

Text #7

Max Range: 2.4787. Min Range: -2.4787

Max Act: 2.1859. Min Act: -0.0000

Data Index: 171503 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 2.4787. Min Range: -2.4787

Max Act: 2.1417. Min Act: -0.0000

Data Index: 64208 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 2.4787. Min Range: -2.4787

Max Act: 1.9777. Min Act: -0.0000

Data Index: 1307471 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 2.4787. Min Range: -2.4787

Max Act: 1.8178. Min Act: -0.0000

Data Index: 78768 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 2.4787. Min Range: -2.4787

Max Act: 1.9223. Min Act: -0.0000

Data Index: 990675 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 2.4787. Min Range: -2.4787

Max Act: 1.8741. Min Act: -0.0000

Data Index: 703336 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 2.4787. Min Range: -2.4787

Max Act: 1.8655. Min Act: -0.0000

Data Index: 74163 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 2.4787. Min Range: -2.4787

Max Act: 1.8491. Min Act: -0.0000

Data Index: 762065 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 2.4787. Min Range: -2.4787

Max Act: 1.8305. Min Act: -0.0000

Data Index: 727413 (C4 (Web Text))

Max Activating Token Index: 589

Text #16

Max Range: 2.4787. Min Range: -2.4787

Max Act: 1.7133. Min Act: -0.0000

Data Index: 210230 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 2.4787. Min Range: -2.4787

Max Act: 1.7056. Min Act: -0.0000

Data Index: 400964 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 2.4787. Min Range: -2.4787

Max Act: 1.8711. Min Act: -0.0000

Data Index: 6595 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 2.4787. Min Range: -2.4787

Max Act: 1.7519. Min Act: -0.0000

Data Index: 254853 (C4 (Web Text))

Max Activating Token Index: 513