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

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

Neuron 3569 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: 2.1419. Min Range: -2.1419

Max Act: 2.0884. Min Act: -0.0000

Data Index: 38566 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 2.1419. Min Range: -2.1419

Max Act: 2.1419. Min Act: -0.0000

Data Index: 1544475 (Python Code)

Max Activating Token Index: 743

Text #2

Max Range: 2.1419. Min Range: -2.1419

Max Act: 2.1091. Min Act: -0.0000

Data Index: 1396777 (Python Code)

Max Activating Token Index: 617

Text #3

Max Range: 2.1419. Min Range: -2.1419

Max Act: 1.9902. Min Act: -0.0000

Data Index: 552044 (C4 (Web Text))

Max Activating Token Index: 207

Text #4

Max Range: 2.1419. Min Range: -2.1419

Max Act: 1.9960. Min Act: -0.0000

Data Index: 1432521 (Python Code)

Max Activating Token Index: 79

Text #5

Max Range: 2.1419. Min Range: -2.1419

Max Act: 1.9766. Min Act: -0.0000

Data Index: 1315287 (C4 (Web Text))

Max Activating Token Index: 327

Text #6

Max Range: 2.1419. Min Range: -2.1419

Max Act: 1.9630. Min Act: -0.0000

Data Index: 1589672 (Python Code)

Max Activating Token Index: 22

Text #7

Max Range: 2.1419. Min Range: -2.1419

Max Act: 1.9532. Min Act: -0.0000

Data Index: 1552971 (Python Code)

Max Activating Token Index: 378

Text #8

Max Range: 2.1419. Min Range: -2.1419

Max Act: 1.7329. Min Act: -0.0000

Data Index: 1446515 (Python Code)

Max Activating Token Index: 28

Text #9

Max Range: 2.1419. Min Range: -2.1419

Max Act: 1.8008. Min Act: -0.0000

Data Index: 776328 (C4 (Web Text))

Max Activating Token Index: 226

Text #10

Max Range: 2.1419. Min Range: -2.1419

Max Act: 2.0114. Min Act: -0.0000

Data Index: 1656171 (Python Code)

Max Activating Token Index: 812

Text #11

Max Range: 2.1419. Min Range: -2.1419

Max Act: 1.9922. Min Act: -0.0000

Data Index: 1574460 (Python Code)

Max Activating Token Index: 469

Text #12

Max Range: 2.1419. Min Range: -2.1419

Max Act: 1.8885. Min Act: -0.0000

Data Index: 1534612 (Python Code)

Max Activating Token Index: 955

Text #13

Max Range: 2.1419. Min Range: -2.1419

Max Act: 1.8984. Min Act: -0.0000

Data Index: 834292 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 2.1419. Min Range: -2.1419

Max Act: 1.9907. Min Act: -0.0000

Data Index: 1401703 (Python Code)

Max Activating Token Index: 851

Text #15

Max Range: 2.1419. Min Range: -2.1419

Max Act: 1.7592. Min Act: -0.0000

Data Index: 1411038 (Python Code)

Max Activating Token Index: 45

Text #16

Max Range: 2.1419. Min Range: -2.1419

Max Act: 1.9166. Min Act: -0.0000

Data Index: 1122798 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 2.1419. Min Range: -2.1419

Max Act: 1.7240. Min Act: -0.0000

Data Index: 1632674 (Python Code)

Max Activating Token Index: 130

Text #18

Max Range: 2.1419. Min Range: -2.1419

Max Act: 1.7538. Min Act: -0.0000

Data Index: 914435 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 2.1419. Min Range: -2.1419

Max Act: 1.7679. Min Act: -0.0000

Data Index: 1636020 (Python Code)

Max Activating Token Index: 93