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

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

Neuron 3431 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9563. Min Range: -1.9563

Max Act: 1.9251. Min Act: -0.0001

Data Index: 1445453 (Python Code)

Max Activating Token Index: 512

Text #1

Max Range: 1.9563. Min Range: -1.9563

Max Act: 1.9563. Min Act: -0.0001

Data Index: 1430083 (Python Code)

Max Activating Token Index: 403

Text #2

Max Range: 1.9563. Min Range: -1.9563

Max Act: 1.7662. Min Act: -0.0000

Data Index: 1529248 (Python Code)

Max Activating Token Index: 699

Text #3

Max Range: 1.9563. Min Range: -1.9563

Max Act: 1.8485. Min Act: -0.0001

Data Index: 1422838 (Python Code)

Max Activating Token Index: 511

Text #4

Max Range: 1.9563. Min Range: -1.9563

Max Act: 1.6586. Min Act: -0.0000

Data Index: 786224 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 1.9563. Min Range: -1.9563

Max Act: 1.7393. Min Act: -0.0001

Data Index: 1429885 (Python Code)

Max Activating Token Index: 76

Text #6

Max Range: 1.9563. Min Range: -1.9563

Max Act: 1.7543. Min Act: -0.0000

Data Index: 1584886 (Python Code)

Max Activating Token Index: 980

Text #7

Max Range: 1.9563. Min Range: -1.9563

Max Act: 1.7738. Min Act: -0.0000

Data Index: 1517279 (Python Code)

Max Activating Token Index: 756

Text #8

Max Range: 1.9563. Min Range: -1.9563

Max Act: 1.7039. Min Act: -0.0001

Data Index: 1640472 (Python Code)

Max Activating Token Index: 398

Text #9

Max Range: 1.9563. Min Range: -1.9563

Max Act: 1.6826. Min Act: -0.0001

Data Index: 1509531 (Python Code)

Max Activating Token Index: 211

Text #10

Max Range: 1.9563. Min Range: -1.9563

Max Act: 1.6838. Min Act: -0.0001

Data Index: 1551770 (Python Code)

Max Activating Token Index: 393

Text #11

Max Range: 1.9563. Min Range: -1.9563

Max Act: 1.6590. Min Act: -0.0000

Data Index: 582348 (C4 (Web Text))

Max Activating Token Index: 618

Text #12

Max Range: 1.9563. Min Range: -1.9563

Max Act: 1.6758. Min Act: -0.0001

Data Index: 1556876 (Python Code)

Max Activating Token Index: 517

Text #13

Max Range: 1.9563. Min Range: -1.9563

Max Act: 1.7029. Min Act: -0.0001

Data Index: 1361602 (Python Code)

Max Activating Token Index: 97

Text #14

Max Range: 1.9563. Min Range: -1.9563

Max Act: 1.5597. Min Act: -0.0000

Data Index: 1590029 (Python Code)

Max Activating Token Index: 104

Text #15

Max Range: 1.9563. Min Range: -1.9563

Max Act: 1.6319. Min Act: -0.0000

Data Index: 1652962 (Python Code)

Max Activating Token Index: 940

Text #16

Max Range: 1.9563. Min Range: -1.9563

Max Act: 1.6753. Min Act: -0.0001

Data Index: 1619443 (Python Code)

Max Activating Token Index: 1019

Text #17

Max Range: 1.9563. Min Range: -1.9563

Max Act: 1.6259. Min Act: -0.0001

Data Index: 1480099 (Python Code)

Max Activating Token Index: 569

Text #18

Max Range: 1.9563. Min Range: -1.9563

Max Act: 1.5386. Min Act: -0.0001

Data Index: 1652590 (Python Code)

Max Activating Token Index: 634

Text #19

Max Range: 1.9563. Min Range: -1.9563

Max Act: 1.6054. Min Act: -0.0001

Data Index: 1510070 (Python Code)

Max Activating Token Index: 62