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

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

Neuron 871 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.9880. Min Act: -0.0001

Data Index: 1453277 (Python Code)

Max Activating Token Index: 26

Text #1

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.9544. Min Act: -0.0001

Data Index: 1582561 (Python Code)

Max Activating Token Index: 112

Text #2

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.9392. Min Act: -0.0001

Data Index: 1556105 (Python Code)

Max Activating Token Index: 120

Text #3

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.8967. Min Act: -0.0001

Data Index: 1407527 (Python Code)

Max Activating Token Index: 176

Text #4

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.9596. Min Act: -0.0001

Data Index: 1561497 (Python Code)

Max Activating Token Index: 87

Text #5

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.9118. Min Act: -0.0001

Data Index: 1401368 (Python Code)

Max Activating Token Index: 91

Text #6

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.9072. Min Act: -0.0001

Data Index: 1641430 (Python Code)

Max Activating Token Index: 192

Text #7

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.8628. Min Act: -0.0001

Data Index: 1362246 (Python Code)

Max Activating Token Index: 57

Text #8

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.8878. Min Act: -0.0001

Data Index: 1425458 (Python Code)

Max Activating Token Index: 306

Text #9

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.8660. Min Act: -0.0001

Data Index: 1579208 (Python Code)

Max Activating Token Index: 76

Text #10

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.8335. Min Act: -0.0001

Data Index: 1631111 (Python Code)

Max Activating Token Index: 190

Text #11

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.9212. Min Act: -0.0001

Data Index: 1569448 (Python Code)

Max Activating Token Index: 594

Text #12

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.8284. Min Act: -0.0001

Data Index: 1485964 (Python Code)

Max Activating Token Index: 83

Text #13

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.8538. Min Act: -0.0001

Data Index: 1614122 (Python Code)

Max Activating Token Index: 427

Text #14

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.8004. Min Act: -0.0001

Data Index: 1399032 (Python Code)

Max Activating Token Index: 312

Text #15

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.8194. Min Act: -0.0001

Data Index: 1530110 (Python Code)

Max Activating Token Index: 219

Text #16

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.7936. Min Act: -0.0001

Data Index: 1581777 (Python Code)

Max Activating Token Index: 69

Text #17

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.7909. Min Act: -0.0001

Data Index: 1635017 (Python Code)

Max Activating Token Index: 263

Text #18

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.8058. Min Act: -0.0001

Data Index: 1610436 (Python Code)

Max Activating Token Index: 404

Text #19

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.8014. Min Act: -0.0001

Data Index: 1621875 (Python Code)

Max Activating Token Index: 364