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

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

Neuron 984 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.6212. Min Act: -0.0001

Data Index: 1474670 (Python Code)

Max Activating Token Index: 166

Text #1

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.7142. Min Act: -0.0001

Data Index: 1656584 (Python Code)

Max Activating Token Index: 251

Text #2

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.7050. Min Act: -0.0001

Data Index: 1437015 (Python Code)

Max Activating Token Index: 4

Text #3

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.6790. Min Act: -0.0001

Data Index: 1609023 (Python Code)

Max Activating Token Index: 31

Text #4

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.6635. Min Act: -0.0001

Data Index: 1510689 (Python Code)

Max Activating Token Index: 5

Text #5

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.7115. Min Act: -0.0001

Data Index: 1626334 (Python Code)

Max Activating Token Index: 784

Text #6

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.6156. Min Act: -0.0001

Data Index: 1613486 (Python Code)

Max Activating Token Index: 27

Text #7

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.5541. Min Act: -0.0001

Data Index: 1527577 (Python Code)

Max Activating Token Index: 318

Text #8

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.6189. Min Act: -0.0001

Data Index: 1391877 (Python Code)

Max Activating Token Index: 14

Text #9

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.5865. Min Act: -0.0001

Data Index: 1443062 (Python Code)

Max Activating Token Index: 77

Text #10

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.5511. Min Act: -0.0001

Data Index: 1613927 (Python Code)

Max Activating Token Index: 364

Text #11

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.5257. Min Act: -0.0001

Data Index: 1552989 (Python Code)

Max Activating Token Index: 382

Text #12

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.5562. Min Act: -0.0001

Data Index: 1613835 (Python Code)

Max Activating Token Index: 73

Text #13

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.5542. Min Act: -0.0001

Data Index: 1464432 (Python Code)

Max Activating Token Index: 776

Text #14

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.5906. Min Act: -0.0001

Data Index: 1469080 (Python Code)

Max Activating Token Index: 127

Text #15

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.5146. Min Act: -0.0001

Data Index: 1592740 (Python Code)

Max Activating Token Index: 830

Text #16

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.5230. Min Act: -0.0001

Data Index: 1606812 (Python Code)

Max Activating Token Index: 502

Text #17

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.5581. Min Act: -0.0001

Data Index: 1420723 (Python Code)

Max Activating Token Index: 605

Text #18

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.5288. Min Act: -0.0001

Data Index: 1422017 (Python Code)

Max Activating Token Index: 804

Text #19

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.5559. Min Act: -0.0001

Data Index: 1651782 (Python Code)

Max Activating Token Index: 243