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

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

Neuron 950 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: 3.1391. Min Range: -3.1391

Max Act: 3.1391. Min Act: -0.0000

Data Index: 1517460 (Python Code)

Max Activating Token Index: 826

Text #1

Max Range: 3.1391. Min Range: -3.1391

Max Act: 2.8239. Min Act: -0.0000

Data Index: 1469072 (Python Code)

Max Activating Token Index: 993

Text #2

Max Range: 3.1391. Min Range: -3.1391

Max Act: 2.8408. Min Act: -0.0000

Data Index: 1447824 (Python Code)

Max Activating Token Index: 793

Text #3

Max Range: 3.1391. Min Range: -3.1391

Max Act: 2.8124. Min Act: -0.0000

Data Index: 1454898 (Python Code)

Max Activating Token Index: 217

Text #4

Max Range: 3.1391. Min Range: -3.1391

Max Act: 2.6820. Min Act: -0.0000

Data Index: 1556405 (Python Code)

Max Activating Token Index: 1002

Text #5

Max Range: 3.1391. Min Range: -3.1391

Max Act: 2.7623. Min Act: -0.0000

Data Index: 1473178 (Python Code)

Max Activating Token Index: 832

Text #6

Max Range: 3.1391. Min Range: -3.1391

Max Act: 2.5974. Min Act: -0.0000

Data Index: 1432076 (Python Code)

Max Activating Token Index: 975

Text #7

Max Range: 3.1391. Min Range: -3.1391

Max Act: 2.4730. Min Act: -0.0000

Data Index: 1495588 (Python Code)

Max Activating Token Index: 1010

Text #8

Max Range: 3.1391. Min Range: -3.1391

Max Act: 2.4981. Min Act: -0.0000

Data Index: 1436271 (Python Code)

Max Activating Token Index: 1005

Text #9

Max Range: 3.1391. Min Range: -3.1391

Max Act: 2.3850. Min Act: -0.0000

Data Index: 1428938 (Python Code)

Max Activating Token Index: 489

Text #10

Max Range: 3.1391. Min Range: -3.1391

Max Act: 2.5007. Min Act: -0.0000

Data Index: 1477613 (Python Code)

Max Activating Token Index: 833

Text #11

Max Range: 3.1391. Min Range: -3.1391

Max Act: 2.3295. Min Act: -0.0000

Data Index: 1526457 (Python Code)

Max Activating Token Index: 980

Text #12

Max Range: 3.1391. Min Range: -3.1391

Max Act: 2.1832. Min Act: -0.0000

Data Index: 1545736 (Python Code)

Max Activating Token Index: 893

Text #13

Max Range: 3.1391. Min Range: -3.1391

Max Act: 2.4207. Min Act: -0.0000

Data Index: 1532042 (Python Code)

Max Activating Token Index: 915

Text #14

Max Range: 3.1391. Min Range: -3.1391

Max Act: 2.3810. Min Act: -0.0000

Data Index: 1618321 (Python Code)

Max Activating Token Index: 184

Text #15

Max Range: 3.1391. Min Range: -3.1391

Max Act: 2.2360. Min Act: -0.0000

Data Index: 1501562 (Python Code)

Max Activating Token Index: 963

Text #16

Max Range: 3.1391. Min Range: -3.1391

Max Act: 2.1126. Min Act: -0.0000

Data Index: 1179132 (C4 (Web Text))

Max Activating Token Index: 658

Text #17

Max Range: 3.1391. Min Range: -3.1391

Max Act: 2.3291. Min Act: -0.0000

Data Index: 1539287 (Python Code)

Max Activating Token Index: 88

Text #18

Max Range: 3.1391. Min Range: -3.1391

Max Act: 2.3329. Min Act: -0.0000

Data Index: 1509591 (Python Code)

Max Activating Token Index: 983

Text #19

Max Range: 3.1391. Min Range: -3.1391

Max Act: 2.3233. Min Act: -0.0000

Data Index: 1571736 (Python Code)

Max Activating Token Index: 1018