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

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

Neuron 935 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2495. Min Act: -0.0000

Data Index: 75358 (C4 (Web Text))

Max Activating Token Index: 513

Text #1

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2268. Min Act: -0.0000

Data Index: 1410524 (Python Code)

Max Activating Token Index: 362

Text #2

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2005. Min Act: -0.0000

Data Index: 653718 (C4 (Web Text))

Max Activating Token Index: 619

Text #3

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.2043. Min Act: -0.0000

Data Index: 1399141 (Python Code)

Max Activating Token Index: 640

Text #4

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1836. Min Act: -0.0000

Data Index: 373189 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1715. Min Act: 0.0000

Data Index: 815135 (C4 (Web Text))

Max Activating Token Index: 505

Text #6

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1766. Min Act: -0.0000

Data Index: 945692 (C4 (Web Text))

Max Activating Token Index: 981

Text #7

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1672. Min Act: -0.0000

Data Index: 976452 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1527. Min Act: -0.0000

Data Index: 753323 (C4 (Web Text))

Max Activating Token Index: 288

Text #9

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1509. Min Act: -0.0000

Data Index: 1143712 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1561. Min Act: -0.0000

Data Index: 1643886 (Python Code)

Max Activating Token Index: 360

Text #11

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1423. Min Act: 0.0000

Data Index: 697798 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1476. Min Act: -0.0000

Data Index: 71053 (C4 (Web Text))

Max Activating Token Index: 649

Text #13

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1529. Min Act: -0.0000

Data Index: 1131540 (C4 (Web Text))

Max Activating Token Index: 742

Text #14

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1566. Min Act: -0.0000

Data Index: 821732 (C4 (Web Text))

Max Activating Token Index: 524

Text #15

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1503. Min Act: -0.0000

Data Index: 526985 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1473. Min Act: -0.0000

Data Index: 1543521 (Python Code)

Max Activating Token Index: 992

Text #17

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1358. Min Act: -0.0000

Data Index: 303381 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1386. Min Act: 0.0000

Data Index: 732749 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 0.2495. Min Range: -0.2495

Max Act: 0.1470. Min Act: -0.0000

Data Index: 381601 (C4 (Web Text))

Max Activating Token Index: 645