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

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

Neuron 208 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5433. Min Range: -1.5433

Max Act: 1.5433. Min Act: -0.0000

Data Index: 914656 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 1.5433. Min Range: -1.5433

Max Act: 1.5060. Min Act: -0.0000

Data Index: 102055 (C4 (Web Text))

Max Activating Token Index: 800

Text #2

Max Range: 1.5433. Min Range: -1.5433

Max Act: 1.3963. Min Act: -0.0000

Data Index: 976616 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 1.5433. Min Range: -1.5433

Max Act: 1.3060. Min Act: -0.0000

Data Index: 404135 (C4 (Web Text))

Max Activating Token Index: 949

Text #4

Max Range: 1.5433. Min Range: -1.5433

Max Act: 1.3843. Min Act: -0.0000

Data Index: 987583 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 1.5433. Min Range: -1.5433

Max Act: 1.2881. Min Act: -0.0000

Data Index: 854569 (C4 (Web Text))

Max Activating Token Index: 440

Text #6

Max Range: 1.5433. Min Range: -1.5433

Max Act: 1.2630. Min Act: -0.0000

Data Index: 170920 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 1.5433. Min Range: -1.5433

Max Act: 1.2990. Min Act: -0.0000

Data Index: 165274 (C4 (Web Text))

Max Activating Token Index: 976

Text #8

Max Range: 1.5433. Min Range: -1.5433

Max Act: 1.2404. Min Act: -0.0000

Data Index: 650801 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 1.5433. Min Range: -1.5433

Max Act: 1.2005. Min Act: -0.0000

Data Index: 397303 (C4 (Web Text))

Max Activating Token Index: 907

Text #10

Max Range: 1.5433. Min Range: -1.5433

Max Act: 1.2508. Min Act: -0.0000

Data Index: 360915 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 1.5433. Min Range: -1.5433

Max Act: 1.1941. Min Act: -0.0000

Data Index: 1560644 (Python Code)

Max Activating Token Index: 553

Text #12

Max Range: 1.5433. Min Range: -1.5433

Max Act: 1.2281. Min Act: -0.0000

Data Index: 438018 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 1.5433. Min Range: -1.5433

Max Act: 1.2316. Min Act: -0.0000

Data Index: 589204 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 1.5433. Min Range: -1.5433

Max Act: 1.2141. Min Act: -0.0000

Data Index: 1543317 (Python Code)

Max Activating Token Index: 371

Text #15

Max Range: 1.5433. Min Range: -1.5433

Max Act: 1.2342. Min Act: -0.0000

Data Index: 1340799 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 1.5433. Min Range: -1.5433

Max Act: 1.2369. Min Act: -0.0000

Data Index: 571124 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 1.5433. Min Range: -1.5433

Max Act: 1.1656. Min Act: -0.0000

Data Index: 1650904 (Python Code)

Max Activating Token Index: 829

Text #18

Max Range: 1.5433. Min Range: -1.5433

Max Act: 1.2023. Min Act: -0.0000

Data Index: 479111 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 1.5433. Min Range: -1.5433

Max Act: 1.1606. Min Act: -0.0000

Data Index: 1442768 (Python Code)

Max Activating Token Index: 713