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

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

Neuron 203 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7982. Min Range: -1.7982

Max Act: 1.7084. Min Act: -0.0002

Data Index: 201524 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 1.7982. Min Range: -1.7982

Max Act: 1.4985. Min Act: -0.0002

Data Index: 772628 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 1.7982. Min Range: -1.7982

Max Act: 1.6942. Min Act: -0.0002

Data Index: 751137 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 1.7982. Min Range: -1.7982

Max Act: 1.6462. Min Act: -0.0002

Data Index: 1330039 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 1.7982. Min Range: -1.7982

Max Act: 1.6971. Min Act: -0.0002

Data Index: 1286656 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 1.7982. Min Range: -1.7982

Max Act: 1.4478. Min Act: -0.0002

Data Index: 1180426 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 1.7982. Min Range: -1.7982

Max Act: 1.4584. Min Act: -0.0002

Data Index: 169487 (C4 (Web Text))

Max Activating Token Index: 923

Text #7

Max Range: 1.7982. Min Range: -1.7982

Max Act: 1.1837. Min Act: -0.0002

Data Index: 249136 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 1.7982. Min Range: -1.7982

Max Act: 1.2110. Min Act: -0.0002

Data Index: 950185 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 1.7982. Min Range: -1.7982

Max Act: 1.4664. Min Act: -0.0002

Data Index: 87817 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 1.7982. Min Range: -1.7982

Max Act: 1.7241. Min Act: -0.0002

Data Index: 1274488 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 1.7982. Min Range: -1.7982

Max Act: 1.7982. Min Act: -0.0002

Data Index: 611823 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 1.7982. Min Range: -1.7982

Max Act: 1.5700. Min Act: -0.0002

Data Index: 160564 (C4 (Web Text))

Max Activating Token Index: 713

Text #13

Max Range: 1.7982. Min Range: -1.7982

Max Act: 1.3539. Min Act: -0.0002

Data Index: 987024 (C4 (Web Text))

Max Activating Token Index: 486

Text #14

Max Range: 1.7982. Min Range: -1.7982

Max Act: 1.6506. Min Act: -0.0002

Data Index: 511434 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 1.7982. Min Range: -1.7982

Max Act: 1.4729. Min Act: -0.0002

Data Index: 732002 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 1.7982. Min Range: -1.7982

Max Act: 1.7480. Min Act: -0.0002

Data Index: 251622 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 1.7982. Min Range: -1.7982

Max Act: 1.5399. Min Act: -0.0002

Data Index: 531407 (C4 (Web Text))

Max Activating Token Index: 578

Text #18

Max Range: 1.7982. Min Range: -1.7982

Max Act: 1.3645. Min Act: -0.0002

Data Index: 841822 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 1.7982. Min Range: -1.7982

Max Act: 1.3236. Min Act: -0.0002

Data Index: 1203243 (C4 (Web Text))

Max Activating Token Index: 164