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

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

Neuron 2472 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1694. Min Range: -2.1694

Max Act: 2.1694. Min Act: -0.0000

Data Index: 1363810 (Python Code)

Max Activating Token Index: 334

Text #1

Max Range: 2.1694. Min Range: -2.1694

Max Act: 1.9931. Min Act: -0.0000

Data Index: 1433182 (Python Code)

Max Activating Token Index: 100

Text #2

Max Range: 2.1694. Min Range: -2.1694

Max Act: 1.8993. Min Act: -0.0000

Data Index: 1450418 (Python Code)

Max Activating Token Index: 239

Text #3

Max Range: 2.1694. Min Range: -2.1694

Max Act: 1.8652. Min Act: -0.0000

Data Index: 1515399 (Python Code)

Max Activating Token Index: 154

Text #4

Max Range: 2.1694. Min Range: -2.1694

Max Act: 1.7323. Min Act: -0.0000

Data Index: 1456226 (Python Code)

Max Activating Token Index: 883

Text #5

Max Range: 2.1694. Min Range: -2.1694

Max Act: 1.7886. Min Act: -0.0000

Data Index: 1367337 (Python Code)

Max Activating Token Index: 211

Text #6

Max Range: 2.1694. Min Range: -2.1694

Max Act: 1.8414. Min Act: -0.0000

Data Index: 1451051 (Python Code)

Max Activating Token Index: 20

Text #7

Max Range: 2.1694. Min Range: -2.1694

Max Act: 1.7456. Min Act: -0.0000

Data Index: 1521320 (Python Code)

Max Activating Token Index: 581

Text #8

Max Range: 2.1694. Min Range: -2.1694

Max Act: 1.7314. Min Act: -0.0000

Data Index: 1420247 (Python Code)

Max Activating Token Index: 131

Text #9

Max Range: 2.1694. Min Range: -2.1694

Max Act: 1.7326. Min Act: -0.0000

Data Index: 1409857 (Python Code)

Max Activating Token Index: 644

Text #10

Max Range: 2.1694. Min Range: -2.1694

Max Act: 1.7118. Min Act: -0.0000

Data Index: 1414723 (Python Code)

Max Activating Token Index: 49

Text #11

Max Range: 2.1694. Min Range: -2.1694

Max Act: 1.7747. Min Act: -0.0000

Data Index: 1491923 (Python Code)

Max Activating Token Index: 127

Text #12

Max Range: 2.1694. Min Range: -2.1694

Max Act: 1.5761. Min Act: -0.0000

Data Index: 1531869 (Python Code)

Max Activating Token Index: 82

Text #13

Max Range: 2.1694. Min Range: -2.1694

Max Act: 1.5733. Min Act: -0.0000

Data Index: 1451170 (Python Code)

Max Activating Token Index: 766

Text #14

Max Range: 2.1694. Min Range: -2.1694

Max Act: 1.6477. Min Act: -0.0000

Data Index: 1360778 (Python Code)

Max Activating Token Index: 384

Text #15

Max Range: 2.1694. Min Range: -2.1694

Max Act: 1.6451. Min Act: -0.0000

Data Index: 1511088 (Python Code)

Max Activating Token Index: 556

Text #16

Max Range: 2.1694. Min Range: -2.1694

Max Act: 1.6271. Min Act: -0.0000

Data Index: 1641982 (Python Code)

Max Activating Token Index: 311

Text #17

Max Range: 2.1694. Min Range: -2.1694

Max Act: 1.6110. Min Act: -0.0000

Data Index: 1546906 (Python Code)

Max Activating Token Index: 106

Text #18

Max Range: 2.1694. Min Range: -2.1694

Max Act: 1.6017. Min Act: -0.0000

Data Index: 1582745 (Python Code)

Max Activating Token Index: 62

Text #19

Max Range: 2.1694. Min Range: -2.1694

Max Act: 1.5781. Min Act: -0.0000

Data Index: 1613103 (Python Code)

Max Activating Token Index: 172