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

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

Neuron 2567 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.9905. Min Act: -0.0000

Data Index: 1389039 (Python Code)

Max Activating Token Index: 990

Text #1

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.7492. Min Act: -0.0000

Data Index: 1496015 (Python Code)

Max Activating Token Index: 299

Text #2

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.7175. Min Act: -0.0000

Data Index: 183907 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.6247. Min Act: -0.0000

Data Index: 523642 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.6822. Min Act: -0.0000

Data Index: 1510362 (Python Code)

Max Activating Token Index: 528

Text #5

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.6994. Min Act: -0.0000

Data Index: 500240 (C4 (Web Text))

Max Activating Token Index: 361

Text #6

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.6038. Min Act: -0.0000

Data Index: 1469417 (Python Code)

Max Activating Token Index: 63

Text #7

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.6581. Min Act: -0.0000

Data Index: 1591699 (Python Code)

Max Activating Token Index: 1000

Text #8

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.6314. Min Act: -0.0000

Data Index: 1538304 (Python Code)

Max Activating Token Index: 150

Text #9

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.5832. Min Act: -0.0000

Data Index: 1470288 (Python Code)

Max Activating Token Index: 368

Text #10

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.6172. Min Act: -0.0000

Data Index: 1656552 (Python Code)

Max Activating Token Index: 521

Text #11

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.6015. Min Act: -0.0000

Data Index: 1420349 (Python Code)

Max Activating Token Index: 87

Text #12

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.5976. Min Act: -0.0000

Data Index: 1594799 (Python Code)

Max Activating Token Index: 235

Text #13

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.5733. Min Act: -0.0000

Data Index: 1405177 (Python Code)

Max Activating Token Index: 276

Text #14

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.5285. Min Act: -0.0000

Data Index: 1360022 (Python Code)

Max Activating Token Index: 254

Text #15

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.6165. Min Act: -0.0000

Data Index: 1653078 (Python Code)

Max Activating Token Index: 166

Text #16

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.5410. Min Act: -0.0000

Data Index: 1514451 (Python Code)

Max Activating Token Index: 1012

Text #17

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.5203. Min Act: -0.0000

Data Index: 999369 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.5763. Min Act: -0.0000

Data Index: 1480448 (Python Code)

Max Activating Token Index: 152

Text #19

Max Range: 0.9905. Min Range: -0.9905

Max Act: 0.5036. Min Act: -0.0000

Data Index: 1013471 (C4 (Web Text))

Max Activating Token Index: 1018