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

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

Neuron 1725 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.9368. Min Act: -0.0000

Data Index: 1514509 (Python Code)

Max Activating Token Index: 89

Text #1

Max Range: 1.0339. Min Range: -1.0339

Max Act: 1.0002. Min Act: -0.0000

Data Index: 1486401 (Python Code)

Max Activating Token Index: 84

Text #2

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.9436. Min Act: -0.0000

Data Index: 1483523 (Python Code)

Max Activating Token Index: 426

Text #3

Max Range: 1.0339. Min Range: -1.0339

Max Act: 1.0339. Min Act: -0.0001

Data Index: 1493234 (Python Code)

Max Activating Token Index: 219

Text #4

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.8835. Min Act: -0.0000

Data Index: 1559532 (Python Code)

Max Activating Token Index: 96

Text #5

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.8573. Min Act: -0.0000

Data Index: 1572047 (Python Code)

Max Activating Token Index: 81

Text #6

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.9086. Min Act: -0.0000

Data Index: 1468053 (Python Code)

Max Activating Token Index: 367

Text #7

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.8524. Min Act: -0.0001

Data Index: 1487227 (Python Code)

Max Activating Token Index: 272

Text #8

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.8455. Min Act: -0.0000

Data Index: 1499714 (Python Code)

Max Activating Token Index: 92

Text #9

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.9167. Min Act: -0.0001

Data Index: 1389437 (Python Code)

Max Activating Token Index: 798

Text #10

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.8285. Min Act: -0.0001

Data Index: 1440304 (Python Code)

Max Activating Token Index: 241

Text #11

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.8640. Min Act: -0.0000

Data Index: 1519569 (Python Code)

Max Activating Token Index: 63

Text #12

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.8661. Min Act: -0.0000

Data Index: 1653420 (Python Code)

Max Activating Token Index: 86

Text #13

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.8003. Min Act: -0.0001

Data Index: 1304067 (C4 (Web Text))

Max Activating Token Index: 706

Text #14

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.8257. Min Act: -0.0001

Data Index: 1569695 (Python Code)

Max Activating Token Index: 23

Text #15

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.8522. Min Act: -0.0001

Data Index: 1396060 (Python Code)

Max Activating Token Index: 1008

Text #16

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.7766. Min Act: -0.0000

Data Index: 1447136 (Python Code)

Max Activating Token Index: 67

Text #17

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.8070. Min Act: -0.0000

Data Index: 1482461 (Python Code)

Max Activating Token Index: 376

Text #18

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.7599. Min Act: -0.0001

Data Index: 1496402 (Python Code)

Max Activating Token Index: 101

Text #19

Max Range: 1.0339. Min Range: -1.0339

Max Act: 0.8048. Min Act: -0.0001

Data Index: 1499218 (Python Code)

Max Activating Token Index: 690