Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3835 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.5256. Min Act: -0.0001

Data Index: 1552694 (Python Code)

Max Activating Token Index: 544

Text #1

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.5644. Min Act: -0.0001

Data Index: 1620525 (Python Code)

Max Activating Token Index: 299

Text #2

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.4583. Min Act: -0.0001

Data Index: 1451596 (Python Code)

Max Activating Token Index: 582

Text #3

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.4159. Min Act: -0.0001

Data Index: 1486977 (Python Code)

Max Activating Token Index: 134

Text #4

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.4245. Min Act: -0.0001

Data Index: 1533599 (Python Code)

Max Activating Token Index: 180

Text #5

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.3781. Min Act: -0.0001

Data Index: 1420742 (Python Code)

Max Activating Token Index: 82

Text #6

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.3697. Min Act: -0.0001

Data Index: 1499667 (Python Code)

Max Activating Token Index: 217

Text #7

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.3664. Min Act: -0.0000

Data Index: 1617141 (Python Code)

Max Activating Token Index: 204

Text #8

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.3724. Min Act: -0.0001

Data Index: 1444081 (Python Code)

Max Activating Token Index: 102

Text #9

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.3371. Min Act: -0.0001

Data Index: 1455550 (Python Code)

Max Activating Token Index: 341

Text #10

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.3391. Min Act: -0.0001

Data Index: 1510271 (Python Code)

Max Activating Token Index: 398

Text #11

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.3323. Min Act: -0.0000

Data Index: 1408202 (Python Code)

Max Activating Token Index: 920

Text #12

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.3154. Min Act: -0.0001

Data Index: 1380692 (Python Code)

Max Activating Token Index: 338

Text #13

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.3297. Min Act: -0.0001

Data Index: 1462412 (Python Code)

Max Activating Token Index: 232

Text #14

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.3030. Min Act: -0.0001

Data Index: 1393896 (Python Code)

Max Activating Token Index: 801

Text #15

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.3256. Min Act: -0.0001

Data Index: 1532451 (Python Code)

Max Activating Token Index: 488

Text #16

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.3271. Min Act: -0.0001

Data Index: 1362529 (Python Code)

Max Activating Token Index: 680

Text #17

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.3098. Min Act: -0.0001

Data Index: 1518509 (Python Code)

Max Activating Token Index: 26

Text #18

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.2890. Min Act: -0.0001

Data Index: 1486283 (Python Code)

Max Activating Token Index: 115

Text #19

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.3319. Min Act: -0.0001

Data Index: 1417994 (Python Code)

Max Activating Token Index: 851