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

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

Neuron 613 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: 1.4690. Min Range: -1.4690

Max Act: 1.4690. Min Act: -0.0000

Data Index: 1006725 (C4 (Web Text))

Max Activating Token Index: 554

Text #1

Max Range: 1.4690. Min Range: -1.4690

Max Act: 1.3570. Min Act: -0.0000

Data Index: 1003503 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 1.4690. Min Range: -1.4690

Max Act: 1.1836. Min Act: -0.0000

Data Index: 233368 (C4 (Web Text))

Max Activating Token Index: 1017

Text #3

Max Range: 1.4690. Min Range: -1.4690

Max Act: 1.2349. Min Act: -0.0000

Data Index: 1286759 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 1.4690. Min Range: -1.4690

Max Act: 1.2461. Min Act: -0.0000

Data Index: 39164 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 1.4690. Min Range: -1.4690

Max Act: 1.0546. Min Act: -0.0000

Data Index: 589025 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 1.4690. Min Range: -1.4690

Max Act: 1.0537. Min Act: -0.0000

Data Index: 200485 (C4 (Web Text))

Max Activating Token Index: 924

Text #7

Max Range: 1.4690. Min Range: -1.4690

Max Act: 1.0808. Min Act: -0.0000

Data Index: 485577 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 1.4690. Min Range: -1.4690

Max Act: 1.0753. Min Act: -0.0000

Data Index: 744001 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 1.4690. Min Range: -1.4690

Max Act: 1.0044. Min Act: -0.0000

Data Index: 716129 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 1.4690. Min Range: -1.4690

Max Act: 1.1411. Min Act: -0.0000

Data Index: 1091149 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 1.4690. Min Range: -1.4690

Max Act: 1.0315. Min Act: -0.0000

Data Index: 300591 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 1.4690. Min Range: -1.4690

Max Act: 1.0289. Min Act: -0.0000

Data Index: 424474 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 1.4690. Min Range: -1.4690

Max Act: 1.0242. Min Act: -0.0000

Data Index: 1313239 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 1.4690. Min Range: -1.4690

Max Act: 1.0199. Min Act: -0.0000

Data Index: 80095 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 1.4690. Min Range: -1.4690

Max Act: 1.0726. Min Act: -0.0000

Data Index: 356047 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 1.4690. Min Range: -1.4690

Max Act: 1.0010. Min Act: -0.0000

Data Index: 807437 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 1.4690. Min Range: -1.4690

Max Act: 0.9962. Min Act: -0.0000

Data Index: 774107 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 1.4690. Min Range: -1.4690

Max Act: 0.9987. Min Act: -0.0000

Data Index: 227143 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 1.4690. Min Range: -1.4690

Max Act: 0.9987. Min Act: -0.0000

Data Index: 299619 (C4 (Web Text))

Max Activating Token Index: 575