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

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

Neuron 2676 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2517. Min Range: -1.2517

Max Act: 1.2517. Min Act: -0.0000

Data Index: 1605782 (Python Code)

Max Activating Token Index: 727

Text #1

Max Range: 1.2517. Min Range: -1.2517

Max Act: 1.1555. Min Act: -0.0000

Data Index: 1419633 (Python Code)

Max Activating Token Index: 498

Text #2

Max Range: 1.2517. Min Range: -1.2517

Max Act: 1.0031. Min Act: -0.0000

Data Index: 1492020 (Python Code)

Max Activating Token Index: 587

Text #3

Max Range: 1.2517. Min Range: -1.2517

Max Act: 1.0961. Min Act: -0.0000

Data Index: 1420475 (Python Code)

Max Activating Token Index: 447

Text #4

Max Range: 1.2517. Min Range: -1.2517

Max Act: 1.0344. Min Act: -0.0000

Data Index: 1455048 (Python Code)

Max Activating Token Index: 557

Text #5

Max Range: 1.2517. Min Range: -1.2517

Max Act: 0.9802. Min Act: -0.0000

Data Index: 1427997 (Python Code)

Max Activating Token Index: 981

Text #6

Max Range: 1.2517. Min Range: -1.2517

Max Act: 0.9731. Min Act: -0.0000

Data Index: 1474845 (Python Code)

Max Activating Token Index: 547

Text #7

Max Range: 1.2517. Min Range: -1.2517

Max Act: 0.9729. Min Act: -0.0000

Data Index: 1376825 (Python Code)

Max Activating Token Index: 648

Text #8

Max Range: 1.2517. Min Range: -1.2517

Max Act: 1.0035. Min Act: -0.0000

Data Index: 1598433 (Python Code)

Max Activating Token Index: 318

Text #9

Max Range: 1.2517. Min Range: -1.2517

Max Act: 1.0256. Min Act: -0.0000

Data Index: 1559619 (Python Code)

Max Activating Token Index: 923

Text #10

Max Range: 1.2517. Min Range: -1.2517

Max Act: 1.0686. Min Act: -0.0000

Data Index: 1642197 (Python Code)

Max Activating Token Index: 931

Text #11

Max Range: 1.2517. Min Range: -1.2517

Max Act: 0.9435. Min Act: -0.0000

Data Index: 1303819 (C4 (Web Text))

Max Activating Token Index: 497

Text #12

Max Range: 1.2517. Min Range: -1.2517

Max Act: 0.9634. Min Act: -0.0000

Data Index: 1510073 (Python Code)

Max Activating Token Index: 446

Text #13

Max Range: 1.2517. Min Range: -1.2517

Max Act: 0.9231. Min Act: -0.0000

Data Index: 1484091 (Python Code)

Max Activating Token Index: 817

Text #14

Max Range: 1.2517. Min Range: -1.2517

Max Act: 0.9089. Min Act: -0.0000

Data Index: 1569839 (Python Code)

Max Activating Token Index: 991

Text #15

Max Range: 1.2517. Min Range: -1.2517

Max Act: 0.9315. Min Act: -0.0000

Data Index: 1607656 (Python Code)

Max Activating Token Index: 992

Text #16

Max Range: 1.2517. Min Range: -1.2517

Max Act: 0.9268. Min Act: -0.0000

Data Index: 1529617 (Python Code)

Max Activating Token Index: 512

Text #17

Max Range: 1.2517. Min Range: -1.2517

Max Act: 0.8979. Min Act: -0.0000

Data Index: 1576311 (Python Code)

Max Activating Token Index: 592

Text #18

Max Range: 1.2517. Min Range: -1.2517

Max Act: 1.0484. Min Act: -0.0000

Data Index: 1551545 (Python Code)

Max Activating Token Index: 854

Text #19

Max Range: 1.2517. Min Range: -1.2517

Max Act: 0.9028. Min Act: -0.0000

Data Index: 1491371 (Python Code)

Max Activating Token Index: 757