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

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

Neuron 548 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: 1.4305. Min Range: -1.4305

Max Act: 1.4305. Min Act: -0.0000

Data Index: 1650455 (Python Code)

Max Activating Token Index: 42

Text #1

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.2624. Min Act: -0.0000

Data Index: 1474706 (Python Code)

Max Activating Token Index: 692

Text #2

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.1690. Min Act: -0.0000

Data Index: 167113 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.1632. Min Act: -0.0000

Data Index: 1498627 (Python Code)

Max Activating Token Index: 609

Text #4

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.0820. Min Act: -0.0000

Data Index: 1511902 (Python Code)

Max Activating Token Index: 385

Text #5

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.0863. Min Act: -0.0000

Data Index: 1490955 (Python Code)

Max Activating Token Index: 655

Text #6

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.1027. Min Act: -0.0000

Data Index: 1627030 (Python Code)

Max Activating Token Index: 778

Text #7

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.1148. Min Act: -0.0000

Data Index: 1411399 (Python Code)

Max Activating Token Index: 268

Text #8

Max Range: 1.4305. Min Range: -1.4305

Max Act: 0.9884. Min Act: -0.0000

Data Index: 580416 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 1.4305. Min Range: -1.4305

Max Act: 0.9971. Min Act: -0.0000

Data Index: 217580 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 1.4305. Min Range: -1.4305

Max Act: 0.9704. Min Act: -0.0000

Data Index: 1148605 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 1.4305. Min Range: -1.4305

Max Act: 0.9725. Min Act: -0.0000

Data Index: 235483 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 1.4305. Min Range: -1.4305

Max Act: 0.9605. Min Act: -0.0000

Data Index: 248423 (C4 (Web Text))

Max Activating Token Index: 72

Text #13

Max Range: 1.4305. Min Range: -1.4305

Max Act: 0.9604. Min Act: -0.0000

Data Index: 1416261 (Python Code)

Max Activating Token Index: 482

Text #14

Max Range: 1.4305. Min Range: -1.4305

Max Act: 0.9767. Min Act: -0.0000

Data Index: 1507315 (Python Code)

Max Activating Token Index: 176

Text #15

Max Range: 1.4305. Min Range: -1.4305

Max Act: 0.9409. Min Act: -0.0000

Data Index: 976557 (C4 (Web Text))

Max Activating Token Index: 663

Text #16

Max Range: 1.4305. Min Range: -1.4305

Max Act: 0.9436. Min Act: -0.0000

Data Index: 1020106 (C4 (Web Text))

Max Activating Token Index: 438

Text #17

Max Range: 1.4305. Min Range: -1.4305

Max Act: 0.9436. Min Act: -0.0000

Data Index: 172020 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 1.4305. Min Range: -1.4305

Max Act: 0.9164. Min Act: -0.0000

Data Index: 1612372 (Python Code)

Max Activating Token Index: 482

Text #19

Max Range: 1.4305. Min Range: -1.4305

Max Act: 0.8282. Min Act: -0.0000

Data Index: 1413923 (Python Code)

Max Activating Token Index: 940