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

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

Neuron 1201 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5979. Min Range: -1.5979

Max Act: 1.5979. Min Act: -0.0001

Data Index: 1426233 (Python Code)

Max Activating Token Index: 147

Text #1

Max Range: 1.5979. Min Range: -1.5979

Max Act: 1.4548. Min Act: -0.0001

Data Index: 1628519 (Python Code)

Max Activating Token Index: 233

Text #2

Max Range: 1.5979. Min Range: -1.5979

Max Act: 1.3760. Min Act: -0.0001

Data Index: 1651472 (Python Code)

Max Activating Token Index: 880

Text #3

Max Range: 1.5979. Min Range: -1.5979

Max Act: 1.4066. Min Act: -0.0001

Data Index: 1581099 (Python Code)

Max Activating Token Index: 296

Text #4

Max Range: 1.5979. Min Range: -1.5979

Max Act: 1.2203. Min Act: -0.0001

Data Index: 1629787 (Python Code)

Max Activating Token Index: 179

Text #5

Max Range: 1.5979. Min Range: -1.5979

Max Act: 1.1964. Min Act: -0.0000

Data Index: 771419 (C4 (Web Text))

Max Activating Token Index: 223

Text #6

Max Range: 1.5979. Min Range: -1.5979

Max Act: 1.2022. Min Act: -0.0001

Data Index: 1412107 (Python Code)

Max Activating Token Index: 525

Text #7

Max Range: 1.5979. Min Range: -1.5979

Max Act: 1.1646. Min Act: -0.0001

Data Index: 1435496 (Python Code)

Max Activating Token Index: 737

Text #8

Max Range: 1.5979. Min Range: -1.5979

Max Act: 1.0460. Min Act: -0.0001

Data Index: 1474512 (Python Code)

Max Activating Token Index: 647

Text #9

Max Range: 1.5979. Min Range: -1.5979

Max Act: 1.1266. Min Act: -0.0001

Data Index: 1596852 (Python Code)

Max Activating Token Index: 610

Text #10

Max Range: 1.5979. Min Range: -1.5979

Max Act: 1.0539. Min Act: -0.0001

Data Index: 1549122 (Python Code)

Max Activating Token Index: 95

Text #11

Max Range: 1.5979. Min Range: -1.5979

Max Act: 1.0139. Min Act: -0.0001

Data Index: 1645789 (Python Code)

Max Activating Token Index: 640

Text #12

Max Range: 1.5979. Min Range: -1.5979

Max Act: 0.9968. Min Act: -0.0000

Data Index: 1620991 (Python Code)

Max Activating Token Index: 158

Text #13

Max Range: 1.5979. Min Range: -1.5979

Max Act: 1.0166. Min Act: -0.0000

Data Index: 1111827 (C4 (Web Text))

Max Activating Token Index: 532

Text #14

Max Range: 1.5979. Min Range: -1.5979

Max Act: 1.0220. Min Act: -0.0001

Data Index: 1469543 (Python Code)

Max Activating Token Index: 377

Text #15

Max Range: 1.5979. Min Range: -1.5979

Max Act: 0.9870. Min Act: -0.0000

Data Index: 1458367 (Python Code)

Max Activating Token Index: 747

Text #16

Max Range: 1.5979. Min Range: -1.5979

Max Act: 0.8133. Min Act: -0.0001

Data Index: 1636751 (Python Code)

Max Activating Token Index: 388

Text #17

Max Range: 1.5979. Min Range: -1.5979

Max Act: 0.9048. Min Act: -0.0000

Data Index: 1610085 (Python Code)

Max Activating Token Index: 639

Text #18

Max Range: 1.5979. Min Range: -1.5979

Max Act: 0.7924. Min Act: -0.0001

Data Index: 1466860 (Python Code)

Max Activating Token Index: 988

Text #19

Max Range: 1.5979. Min Range: -1.5979

Max Act: 0.8454. Min Act: -0.0001

Data Index: 1134190 (C4 (Web Text))

Max Activating Token Index: 706