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

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

Neuron 1987 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0492. Min Range: -3.0492

Max Act: 3.0492. Min Act: -0.0000

Data Index: 1445608 (Python Code)

Max Activating Token Index: 437

Text #1

Max Range: 3.0492. Min Range: -3.0492

Max Act: 2.8385. Min Act: -0.0000

Data Index: 1520016 (Python Code)

Max Activating Token Index: 811

Text #2

Max Range: 3.0492. Min Range: -3.0492

Max Act: 2.3808. Min Act: -0.0000

Data Index: 1595732 (Python Code)

Max Activating Token Index: 488

Text #3

Max Range: 3.0492. Min Range: -3.0492

Max Act: 2.4579. Min Act: -0.0000

Data Index: 1526548 (Python Code)

Max Activating Token Index: 657

Text #4

Max Range: 3.0492. Min Range: -3.0492

Max Act: 2.2710. Min Act: -0.0000

Data Index: 1536933 (Python Code)

Max Activating Token Index: 880

Text #5

Max Range: 3.0492. Min Range: -3.0492

Max Act: 2.5024. Min Act: -0.0000

Data Index: 1599092 (Python Code)

Max Activating Token Index: 967

Text #6

Max Range: 3.0492. Min Range: -3.0492

Max Act: 2.3501. Min Act: -0.0000

Data Index: 1462794 (Python Code)

Max Activating Token Index: 703

Text #7

Max Range: 3.0492. Min Range: -3.0492

Max Act: 2.3650. Min Act: -0.0000

Data Index: 1581608 (Python Code)

Max Activating Token Index: 763

Text #8

Max Range: 3.0492. Min Range: -3.0492

Max Act: 2.3500. Min Act: -0.0000

Data Index: 1580957 (Python Code)

Max Activating Token Index: 512

Text #9

Max Range: 3.0492. Min Range: -3.0492

Max Act: 2.3274. Min Act: -0.0000

Data Index: 1432788 (Python Code)

Max Activating Token Index: 473

Text #10

Max Range: 3.0492. Min Range: -3.0492

Max Act: 2.3021. Min Act: -0.0000

Data Index: 1425359 (Python Code)

Max Activating Token Index: 474

Text #11

Max Range: 3.0492. Min Range: -3.0492

Max Act: 2.1210. Min Act: -0.0000

Data Index: 1367589 (Python Code)

Max Activating Token Index: 733

Text #12

Max Range: 3.0492. Min Range: -3.0492

Max Act: 2.2310. Min Act: -0.0000

Data Index: 1438773 (Python Code)

Max Activating Token Index: 818

Text #13

Max Range: 3.0492. Min Range: -3.0492

Max Act: 2.1759. Min Act: -0.0000

Data Index: 1630345 (Python Code)

Max Activating Token Index: 633

Text #14

Max Range: 3.0492. Min Range: -3.0492

Max Act: 2.1958. Min Act: -0.0000

Data Index: 1641184 (Python Code)

Max Activating Token Index: 378

Text #15

Max Range: 3.0492. Min Range: -3.0492

Max Act: 2.1620. Min Act: -0.0000

Data Index: 1608764 (Python Code)

Max Activating Token Index: 513

Text #16

Max Range: 3.0492. Min Range: -3.0492

Max Act: 2.0508. Min Act: -0.0000

Data Index: 1645668 (Python Code)

Max Activating Token Index: 829

Text #17

Max Range: 3.0492. Min Range: -3.0492

Max Act: 2.1540. Min Act: -0.0000

Data Index: 1656234 (Python Code)

Max Activating Token Index: 851

Text #18

Max Range: 3.0492. Min Range: -3.0492

Max Act: 2.1552. Min Act: -0.0000

Data Index: 1480460 (Python Code)

Max Activating Token Index: 749

Text #19

Max Range: 3.0492. Min Range: -3.0492

Max Act: 2.1353. Min Act: -0.0000

Data Index: 1444854 (Python Code)

Max Activating Token Index: 110