Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1177 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.3479. Min Range: -2.3479

Max Act: 2.3479. Min Act: -0.0000

Data Index: 1578131 (Python Code)

Max Activating Token Index: 130

Text #1

Max Range: 2.3479. Min Range: -2.3479

Max Act: 2.0933. Min Act: -0.0000

Data Index: 1444892 (Python Code)

Max Activating Token Index: 582

Text #2

Max Range: 2.3479. Min Range: -2.3479

Max Act: 1.7838. Min Act: -0.0000

Data Index: 1409203 (Python Code)

Max Activating Token Index: 284

Text #3

Max Range: 2.3479. Min Range: -2.3479

Max Act: 1.8359. Min Act: -0.0000

Data Index: 1446585 (Python Code)

Max Activating Token Index: 958

Text #4

Max Range: 2.3479. Min Range: -2.3479

Max Act: 1.6701. Min Act: 0.0000

Data Index: 1447522 (Python Code)

Max Activating Token Index: 941

Text #5

Max Range: 2.3479. Min Range: -2.3479

Max Act: 1.4961. Min Act: 0.0000

Data Index: 1539366 (Python Code)

Max Activating Token Index: 606

Text #6

Max Range: 2.3479. Min Range: -2.3479

Max Act: 1.4956. Min Act: -0.0000

Data Index: 1374353 (Python Code)

Max Activating Token Index: 956

Text #7

Max Range: 2.3479. Min Range: -2.3479

Max Act: 1.4448. Min Act: -0.0000

Data Index: 1616101 (Python Code)

Max Activating Token Index: 264

Text #8

Max Range: 2.3479. Min Range: -2.3479

Max Act: 1.5059. Min Act: -0.0000

Data Index: 778631 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 2.3479. Min Range: -2.3479

Max Act: 1.5342. Min Act: -0.0000

Data Index: 1520409 (Python Code)

Max Activating Token Index: 788

Text #10

Max Range: 2.3479. Min Range: -2.3479

Max Act: 1.3725. Min Act: -0.0000

Data Index: 1384216 (Python Code)

Max Activating Token Index: 896

Text #11

Max Range: 2.3479. Min Range: -2.3479

Max Act: 1.5181. Min Act: -0.0000

Data Index: 1573587 (Python Code)

Max Activating Token Index: 930

Text #12

Max Range: 2.3479. Min Range: -2.3479

Max Act: 1.4649. Min Act: -0.0000

Data Index: 1417227 (Python Code)

Max Activating Token Index: 292

Text #13

Max Range: 2.3479. Min Range: -2.3479

Max Act: 1.4286. Min Act: 0.0000

Data Index: 1508712 (Python Code)

Max Activating Token Index: 761

Text #14

Max Range: 2.3479. Min Range: -2.3479

Max Act: 1.4118. Min Act: -0.0000

Data Index: 152374 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 2.3479. Min Range: -2.3479

Max Act: 1.4182. Min Act: -0.0000

Data Index: 1270955 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 2.3479. Min Range: -2.3479

Max Act: 1.4617. Min Act: -0.0000

Data Index: 465167 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 2.3479. Min Range: -2.3479

Max Act: 1.3707. Min Act: 0.0000

Data Index: 1432844 (Python Code)

Max Activating Token Index: 724

Text #18

Max Range: 2.3479. Min Range: -2.3479

Max Act: 1.4519. Min Act: -0.0000

Data Index: 1632040 (Python Code)

Max Activating Token Index: 968

Text #19

Max Range: 2.3479. Min Range: -2.3479

Max Act: 1.3471. Min Act: -0.0000

Data Index: 676370 (C4 (Web Text))

Max Activating Token Index: 464