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

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

Neuron 3150 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5595. Min Range: -1.5595

Max Act: 1.5595. Min Act: -0.0001

Data Index: 1426890 (Python Code)

Max Activating Token Index: 14

Text #1

Max Range: 1.5595. Min Range: -1.5595

Max Act: 1.4335. Min Act: -0.0001

Data Index: 1540110 (Python Code)

Max Activating Token Index: 908

Text #2

Max Range: 1.5595. Min Range: -1.5595

Max Act: 1.2294. Min Act: -0.0001

Data Index: 1393656 (Python Code)

Max Activating Token Index: 176

Text #3

Max Range: 1.5595. Min Range: -1.5595

Max Act: 1.2592. Min Act: -0.0001

Data Index: 1615753 (Python Code)

Max Activating Token Index: 428

Text #4

Max Range: 1.5595. Min Range: -1.5595

Max Act: 1.1619. Min Act: -0.0001

Data Index: 1465264 (Python Code)

Max Activating Token Index: 23

Text #5

Max Range: 1.5595. Min Range: -1.5595

Max Act: 1.1149. Min Act: -0.0001

Data Index: 1500514 (Python Code)

Max Activating Token Index: 46

Text #6

Max Range: 1.5595. Min Range: -1.5595

Max Act: 1.1111. Min Act: -0.0001

Data Index: 1513456 (Python Code)

Max Activating Token Index: 570

Text #7

Max Range: 1.5595. Min Range: -1.5595

Max Act: 1.1733. Min Act: -0.0001

Data Index: 1497847 (Python Code)

Max Activating Token Index: 13

Text #8

Max Range: 1.5595. Min Range: -1.5595

Max Act: 1.2363. Min Act: -0.0001

Data Index: 1598789 (Python Code)

Max Activating Token Index: 32

Text #9

Max Range: 1.5595. Min Range: -1.5595

Max Act: 1.1009. Min Act: -0.0001

Data Index: 1448887 (Python Code)

Max Activating Token Index: 739

Text #10

Max Range: 1.5595. Min Range: -1.5595

Max Act: 1.0893. Min Act: -0.0001

Data Index: 1532084 (Python Code)

Max Activating Token Index: 347

Text #11

Max Range: 1.5595. Min Range: -1.5595

Max Act: 1.0927. Min Act: -0.0001

Data Index: 1424290 (Python Code)

Max Activating Token Index: 49

Text #12

Max Range: 1.5595. Min Range: -1.5595

Max Act: 1.0537. Min Act: -0.0001

Data Index: 1620418 (Python Code)

Max Activating Token Index: 505

Text #13

Max Range: 1.5595. Min Range: -1.5595

Max Act: 1.1038. Min Act: -0.0001

Data Index: 1619520 (Python Code)

Max Activating Token Index: 40

Text #14

Max Range: 1.5595. Min Range: -1.5595

Max Act: 1.0279. Min Act: -0.0001

Data Index: 1519709 (Python Code)

Max Activating Token Index: 135

Text #15

Max Range: 1.5595. Min Range: -1.5595

Max Act: 1.1279. Min Act: -0.0001

Data Index: 1533942 (Python Code)

Max Activating Token Index: 32

Text #16

Max Range: 1.5595. Min Range: -1.5595

Max Act: 1.0250. Min Act: -0.0001

Data Index: 1439734 (Python Code)

Max Activating Token Index: 57

Text #17

Max Range: 1.5595. Min Range: -1.5595

Max Act: 1.0562. Min Act: -0.0001

Data Index: 1506262 (Python Code)

Max Activating Token Index: 15

Text #18

Max Range: 1.5595. Min Range: -1.5595

Max Act: 1.0477. Min Act: -0.0001

Data Index: 1531911 (Python Code)

Max Activating Token Index: 105

Text #19

Max Range: 1.5595. Min Range: -1.5595

Max Act: 1.0095. Min Act: -0.0001

Data Index: 1509596 (Python Code)

Max Activating Token Index: 674