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

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

Neuron 2025 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: 1.2472. Min Range: -1.2472

Max Act: 1.2472. Min Act: -0.0000

Data Index: 181143 (C4 (Web Text))

Max Activating Token Index: 938

Text #1

Max Range: 1.2472. Min Range: -1.2472

Max Act: 1.1132. Min Act: -0.0000

Data Index: 1006589 (C4 (Web Text))

Max Activating Token Index: 712

Text #2

Max Range: 1.2472. Min Range: -1.2472

Max Act: 1.0528. Min Act: -0.0000

Data Index: 1100655 (C4 (Web Text))

Max Activating Token Index: 616

Text #3

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.9829. Min Act: -0.0000

Data Index: 1566371 (Python Code)

Max Activating Token Index: 784

Text #4

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.9727. Min Act: -0.0000

Data Index: 1403418 (Python Code)

Max Activating Token Index: 610

Text #5

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.9596. Min Act: -0.0000

Data Index: 1464380 (Python Code)

Max Activating Token Index: 651

Text #6

Max Range: 1.2472. Min Range: -1.2472

Max Act: 1.0017. Min Act: 0.0000

Data Index: 173827 (C4 (Web Text))

Max Activating Token Index: 385

Text #7

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.9372. Min Act: -0.0000

Data Index: 1620178 (Python Code)

Max Activating Token Index: 477

Text #8

Max Range: 1.2472. Min Range: -1.2472

Max Act: 1.0002. Min Act: -0.0000

Data Index: 1494683 (Python Code)

Max Activating Token Index: 761

Text #9

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.9785. Min Act: -0.0000

Data Index: 1574426 (Python Code)

Max Activating Token Index: 341

Text #10

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.8736. Min Act: -0.0000

Data Index: 1190384 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.9779. Min Act: 0.0000

Data Index: 1116283 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.8406. Min Act: -0.0000

Data Index: 1218317 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.9501. Min Act: -0.0000

Data Index: 1429049 (Python Code)

Max Activating Token Index: 508

Text #14

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.8774. Min Act: -0.0000

Data Index: 1235065 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.8549. Min Act: -0.0000

Data Index: 969493 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.8944. Min Act: -0.0000

Data Index: 52904 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.7861. Min Act: -0.0000

Data Index: 1155916 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.8286. Min Act: -0.0000

Data Index: 259848 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 1.2472. Min Range: -1.2472

Max Act: 0.8591. Min Act: -0.0000

Data Index: 1633664 (Python Code)

Max Activating Token Index: 22