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

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

Neuron 1337 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: 0.8497. Min Range: -0.8497

Max Act: 0.8497. Min Act: -0.0000

Data Index: 1484414 (Python Code)

Max Activating Token Index: 201

Text #1

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.7999. Min Act: -0.0000

Data Index: 1049395 (C4 (Web Text))

Max Activating Token Index: 510

Text #2

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.7493. Min Act: -0.0000

Data Index: 899957 (C4 (Web Text))

Max Activating Token Index: 754

Text #3

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.6727. Min Act: -0.0000

Data Index: 993603 (C4 (Web Text))

Max Activating Token Index: 382

Text #4

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.6927. Min Act: -0.0000

Data Index: 1508767 (Python Code)

Max Activating Token Index: 219

Text #5

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.7334. Min Act: -0.0000

Data Index: 510859 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.7224. Min Act: -0.0000

Data Index: 816179 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.7414. Min Act: -0.0000

Data Index: 1647766 (Python Code)

Max Activating Token Index: 126

Text #8

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.6858. Min Act: -0.0000

Data Index: 1463389 (Python Code)

Max Activating Token Index: 876

Text #9

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.7075. Min Act: -0.0000

Data Index: 1382168 (Python Code)

Max Activating Token Index: 620

Text #10

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.6741. Min Act: -0.0000

Data Index: 611892 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.6521. Min Act: -0.0000

Data Index: 1626898 (Python Code)

Max Activating Token Index: 22

Text #12

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.6040. Min Act: -0.0000

Data Index: 442578 (C4 (Web Text))

Max Activating Token Index: 634

Text #13

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.6489. Min Act: -0.0000

Data Index: 286196 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.6002. Min Act: -0.0000

Data Index: 1539328 (Python Code)

Max Activating Token Index: 28

Text #15

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.6288. Min Act: -0.0000

Data Index: 704599 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.5720. Min Act: 0.0000

Data Index: 251830 (C4 (Web Text))

Max Activating Token Index: 314

Text #17

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.5899. Min Act: -0.0000

Data Index: 1368302 (Python Code)

Max Activating Token Index: 901

Text #18

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.5895. Min Act: -0.0000

Data Index: 1090401 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.6022. Min Act: -0.0000

Data Index: 1638621 (Python Code)

Max Activating Token Index: 287