Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2135 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4349. Min Range: -2.4349

Max Act: 2.4349. Min Act: -0.0000

Data Index: 1132980 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 2.4349. Min Range: -2.4349

Max Act: 1.5054. Min Act: -0.0000

Data Index: 1413716 (Python Code)

Max Activating Token Index: 698

Text #2

Max Range: 2.4349. Min Range: -2.4349

Max Act: 1.5811. Min Act: -0.0000

Data Index: 1299820 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 2.4349. Min Range: -2.4349

Max Act: 1.4026. Min Act: -0.0000

Data Index: 1108397 (C4 (Web Text))

Max Activating Token Index: 856

Text #4

Max Range: 2.4349. Min Range: -2.4349

Max Act: 1.4763. Min Act: -0.0000

Data Index: 1398798 (Python Code)

Max Activating Token Index: 401

Text #5

Max Range: 2.4349. Min Range: -2.4349

Max Act: 1.4134. Min Act: -0.0000

Data Index: 1405602 (Python Code)

Max Activating Token Index: 415

Text #6

Max Range: 2.4349. Min Range: -2.4349

Max Act: 1.3755. Min Act: -0.0000

Data Index: 1600495 (Python Code)

Max Activating Token Index: 443

Text #7

Max Range: 2.4349. Min Range: -2.4349

Max Act: 1.4360. Min Act: -0.0000

Data Index: 1411347 (Python Code)

Max Activating Token Index: 655

Text #8

Max Range: 2.4349. Min Range: -2.4349

Max Act: 1.3248. Min Act: -0.0000

Data Index: 12570 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 2.4349. Min Range: -2.4349

Max Act: 1.5543. Min Act: -0.0000

Data Index: 465543 (C4 (Web Text))

Max Activating Token Index: 87

Text #10

Max Range: 2.4349. Min Range: -2.4349

Max Act: 1.3306. Min Act: -0.0000

Data Index: 1429698 (Python Code)

Max Activating Token Index: 305

Text #11

Max Range: 2.4349. Min Range: -2.4349

Max Act: 1.2210. Min Act: -0.0000

Data Index: 1490910 (Python Code)

Max Activating Token Index: 597

Text #12

Max Range: 2.4349. Min Range: -2.4349

Max Act: 1.2605. Min Act: -0.0000

Data Index: 1634474 (Python Code)

Max Activating Token Index: 527

Text #13

Max Range: 2.4349. Min Range: -2.4349

Max Act: 1.2427. Min Act: -0.0000

Data Index: 882104 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 2.4349. Min Range: -2.4349

Max Act: 1.1709. Min Act: -0.0000

Data Index: 1162856 (C4 (Web Text))

Max Activating Token Index: 753

Text #15

Max Range: 2.4349. Min Range: -2.4349

Max Act: 1.3568. Min Act: -0.0000

Data Index: 242695 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 2.4349. Min Range: -2.4349

Max Act: 1.2112. Min Act: -0.0000

Data Index: 1430500 (Python Code)

Max Activating Token Index: 169

Text #17

Max Range: 2.4349. Min Range: -2.4349

Max Act: 1.2722. Min Act: -0.0000

Data Index: 1415145 (Python Code)

Max Activating Token Index: 593

Text #18

Max Range: 2.4349. Min Range: -2.4349

Max Act: 1.1715. Min Act: -0.0000

Data Index: 159102 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 2.4349. Min Range: -2.4349

Max Act: 1.2066. Min Act: -0.0000

Data Index: 1530779 (Python Code)

Max Activating Token Index: 426