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

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

Neuron 4707 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5926. Min Range: -0.5926

Max Act: 0.5926. Min Act: -0.0002

Data Index: 1374593 (Python Code)

Max Activating Token Index: 188

Text #1

Max Range: 0.5926. Min Range: -0.5926

Max Act: 0.5765. Min Act: -0.0002

Data Index: 1596542 (Python Code)

Max Activating Token Index: 330

Text #2

Max Range: 0.5926. Min Range: -0.5926

Max Act: 0.5540. Min Act: -0.0002

Data Index: 1508517 (Python Code)

Max Activating Token Index: 172

Text #3

Max Range: 0.5926. Min Range: -0.5926

Max Act: 0.5626. Min Act: -0.0002

Data Index: 1627479 (Python Code)

Max Activating Token Index: 456

Text #4

Max Range: 0.5926. Min Range: -0.5926

Max Act: 0.5232. Min Act: -0.0002

Data Index: 1547188 (Python Code)

Max Activating Token Index: 281

Text #5

Max Range: 0.5926. Min Range: -0.5926

Max Act: 0.5783. Min Act: -0.0002

Data Index: 1650659 (Python Code)

Max Activating Token Index: 314

Text #6

Max Range: 0.5926. Min Range: -0.5926

Max Act: 0.5533. Min Act: -0.0002

Data Index: 1560008 (Python Code)

Max Activating Token Index: 230

Text #7

Max Range: 0.5926. Min Range: -0.5926

Max Act: 0.5375. Min Act: -0.0002

Data Index: 1543215 (Python Code)

Max Activating Token Index: 275

Text #8

Max Range: 0.5926. Min Range: -0.5926

Max Act: 0.5526. Min Act: -0.0002

Data Index: 1426436 (Python Code)

Max Activating Token Index: 483

Text #9

Max Range: 0.5926. Min Range: -0.5926

Max Act: 0.5116. Min Act: -0.0002

Data Index: 1486135 (Python Code)

Max Activating Token Index: 116

Text #10

Max Range: 0.5926. Min Range: -0.5926

Max Act: 0.5452. Min Act: -0.0002

Data Index: 1433115 (Python Code)

Max Activating Token Index: 292

Text #11

Max Range: 0.5926. Min Range: -0.5926

Max Act: 0.5567. Min Act: -0.0002

Data Index: 1614202 (Python Code)

Max Activating Token Index: 311

Text #12

Max Range: 0.5926. Min Range: -0.5926

Max Act: 0.5031. Min Act: -0.0002

Data Index: 1520505 (Python Code)

Max Activating Token Index: 24

Text #13

Max Range: 0.5926. Min Range: -0.5926

Max Act: 0.5213. Min Act: -0.0002

Data Index: 1489731 (Python Code)

Max Activating Token Index: 327

Text #14

Max Range: 0.5926. Min Range: -0.5926

Max Act: 0.5239. Min Act: -0.0002

Data Index: 1391764 (Python Code)

Max Activating Token Index: 369

Text #15

Max Range: 0.5926. Min Range: -0.5926

Max Act: 0.5380. Min Act: -0.0002

Data Index: 1629118 (Python Code)

Max Activating Token Index: 231

Text #16

Max Range: 0.5926. Min Range: -0.5926

Max Act: 0.5221. Min Act: -0.0002

Data Index: 1507306 (Python Code)

Max Activating Token Index: 311

Text #17

Max Range: 0.5926. Min Range: -0.5926

Max Act: 0.5373. Min Act: -0.0002

Data Index: 1618242 (Python Code)

Max Activating Token Index: 83

Text #18

Max Range: 0.5926. Min Range: -0.5926

Max Act: 0.5169. Min Act: -0.0002

Data Index: 1545137 (Python Code)

Max Activating Token Index: 219

Text #19

Max Range: 0.5926. Min Range: -0.5926

Max Act: 0.5338. Min Act: -0.0002

Data Index: 1360615 (Python Code)

Max Activating Token Index: 165