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

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

Neuron 1851 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: 6.2266. Min Range: -6.2266

Max Act: 6.1598. Min Act: -0.0000

Data Index: 1429644 (Python Code)

Max Activating Token Index: 88

Text #1

Max Range: 6.2266. Min Range: -6.2266

Max Act: 6.2266. Min Act: -0.0000

Data Index: 1439894 (Python Code)

Max Activating Token Index: 578

Text #2

Max Range: 6.2266. Min Range: -6.2266

Max Act: 6.1281. Min Act: -0.0000

Data Index: 1416281 (Python Code)

Max Activating Token Index: 128

Text #3

Max Range: 6.2266. Min Range: -6.2266

Max Act: 5.9643. Min Act: -0.0000

Data Index: 1412320 (Python Code)

Max Activating Token Index: 830

Text #4

Max Range: 6.2266. Min Range: -6.2266

Max Act: 5.3996. Min Act: -0.0000

Data Index: 1481966 (Python Code)

Max Activating Token Index: 59

Text #5

Max Range: 6.2266. Min Range: -6.2266

Max Act: 5.6679. Min Act: -0.0000

Data Index: 1646844 (Python Code)

Max Activating Token Index: 395

Text #6

Max Range: 6.2266. Min Range: -6.2266

Max Act: 5.5426. Min Act: -0.0000

Data Index: 1376223 (Python Code)

Max Activating Token Index: 251

Text #7

Max Range: 6.2266. Min Range: -6.2266

Max Act: 4.7159. Min Act: -0.0000

Data Index: 1603280 (Python Code)

Max Activating Token Index: 926

Text #8

Max Range: 6.2266. Min Range: -6.2266

Max Act: 5.4520. Min Act: -0.0000

Data Index: 1500566 (Python Code)

Max Activating Token Index: 993

Text #9

Max Range: 6.2266. Min Range: -6.2266

Max Act: 5.1584. Min Act: -0.0000

Data Index: 1633455 (Python Code)

Max Activating Token Index: 805

Text #10

Max Range: 6.2266. Min Range: -6.2266

Max Act: 5.1376. Min Act: -0.0000

Data Index: 1648678 (Python Code)

Max Activating Token Index: 236

Text #11

Max Range: 6.2266. Min Range: -6.2266

Max Act: 5.1073. Min Act: -0.0000

Data Index: 1632486 (Python Code)

Max Activating Token Index: 393

Text #12

Max Range: 6.2266. Min Range: -6.2266

Max Act: 5.0014. Min Act: -0.0000

Data Index: 1475271 (Python Code)

Max Activating Token Index: 667

Text #13

Max Range: 6.2266. Min Range: -6.2266

Max Act: 5.0038. Min Act: -0.0000

Data Index: 1377090 (Python Code)

Max Activating Token Index: 971

Text #14

Max Range: 6.2266. Min Range: -6.2266

Max Act: 4.7584. Min Act: -0.0000

Data Index: 1398935 (Python Code)

Max Activating Token Index: 877

Text #15

Max Range: 6.2266. Min Range: -6.2266

Max Act: 4.9626. Min Act: -0.0000

Data Index: 1542975 (Python Code)

Max Activating Token Index: 582

Text #16

Max Range: 6.2266. Min Range: -6.2266

Max Act: 4.9403. Min Act: -0.0000

Data Index: 1520841 (Python Code)

Max Activating Token Index: 162

Text #17

Max Range: 6.2266. Min Range: -6.2266

Max Act: 4.9299. Min Act: -0.0000

Data Index: 1629740 (Python Code)

Max Activating Token Index: 921

Text #18

Max Range: 6.2266. Min Range: -6.2266

Max Act: 5.0884. Min Act: -0.0000

Data Index: 1646502 (Python Code)

Max Activating Token Index: 349

Text #19

Max Range: 6.2266. Min Range: -6.2266

Max Act: 4.8760. Min Act: -0.0000

Data Index: 1360161 (Python Code)

Max Activating Token Index: 95