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

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

Neuron 4742 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: 4.2481. Min Range: -4.2481

Max Act: 4.2481. Min Act: 0.0000

Data Index: 1376337 (Python Code)

Max Activating Token Index: 795

Text #1

Max Range: 4.2481. Min Range: -4.2481

Max Act: 3.2204. Min Act: -0.0000

Data Index: 1575031 (Python Code)

Max Activating Token Index: 813

Text #2

Max Range: 4.2481. Min Range: -4.2481

Max Act: 2.7905. Min Act: -0.0000

Data Index: 1368643 (Python Code)

Max Activating Token Index: 979

Text #3

Max Range: 4.2481. Min Range: -4.2481

Max Act: 2.7284. Min Act: -0.0000

Data Index: 1617355 (Python Code)

Max Activating Token Index: 479

Text #4

Max Range: 4.2481. Min Range: -4.2481

Max Act: 2.6844. Min Act: -0.0000

Data Index: 252026 (C4 (Web Text))

Max Activating Token Index: 361

Text #5

Max Range: 4.2481. Min Range: -4.2481

Max Act: 2.4312. Min Act: 0.0000

Data Index: 1615776 (Python Code)

Max Activating Token Index: 351

Text #6

Max Range: 4.2481. Min Range: -4.2481

Max Act: 2.3963. Min Act: -0.0000

Data Index: 1410671 (Python Code)

Max Activating Token Index: 731

Text #7

Max Range: 4.2481. Min Range: -4.2481

Max Act: 2.6586. Min Act: -0.0000

Data Index: 1477665 (Python Code)

Max Activating Token Index: 993

Text #8

Max Range: 4.2481. Min Range: -4.2481

Max Act: 2.3590. Min Act: -0.0000

Data Index: 501219 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 4.2481. Min Range: -4.2481

Max Act: 2.4781. Min Act: -0.0000

Data Index: 874690 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 4.2481. Min Range: -4.2481

Max Act: 2.6455. Min Act: -0.0000

Data Index: 1412107 (Python Code)

Max Activating Token Index: 862

Text #11

Max Range: 4.2481. Min Range: -4.2481

Max Act: 2.7201. Min Act: -0.0000

Data Index: 1539924 (Python Code)

Max Activating Token Index: 420

Text #12

Max Range: 4.2481. Min Range: -4.2481

Max Act: 2.5870. Min Act: -0.0000

Data Index: 1452073 (Python Code)

Max Activating Token Index: 793

Text #13

Max Range: 4.2481. Min Range: -4.2481

Max Act: 2.2202. Min Act: -0.0000

Data Index: 1640421 (Python Code)

Max Activating Token Index: 966

Text #14

Max Range: 4.2481. Min Range: -4.2481

Max Act: 2.2781. Min Act: 0.0001

Data Index: 1645052 (Python Code)

Max Activating Token Index: 212

Text #15

Max Range: 4.2481. Min Range: -4.2481

Max Act: 2.3715. Min Act: -0.0000

Data Index: 1443688 (Python Code)

Max Activating Token Index: 951

Text #16

Max Range: 4.2481. Min Range: -4.2481

Max Act: 2.2447. Min Act: -0.0000

Data Index: 1458985 (Python Code)

Max Activating Token Index: 868

Text #17

Max Range: 4.2481. Min Range: -4.2481

Max Act: 2.3569. Min Act: -0.0000

Data Index: 1509415 (Python Code)

Max Activating Token Index: 898

Text #18

Max Range: 4.2481. Min Range: -4.2481

Max Act: 2.3495. Min Act: 0.0000

Data Index: 1604002 (Python Code)

Max Activating Token Index: 952

Text #19

Max Range: 4.2481. Min Range: -4.2481

Max Act: 2.3515. Min Act: 0.0000

Data Index: 1554614 (Python Code)

Max Activating Token Index: 878