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

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

Neuron 998 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5829. Min Range: -2.5829

Max Act: 2.5302. Min Act: -0.0000

Data Index: 1368714 (Python Code)

Max Activating Token Index: 39

Text #1

Max Range: 2.5829. Min Range: -2.5829

Max Act: 2.5046. Min Act: -0.0000

Data Index: 1622991 (Python Code)

Max Activating Token Index: 659

Text #2

Max Range: 2.5829. Min Range: -2.5829

Max Act: 2.5829. Min Act: -0.0000

Data Index: 1495442 (Python Code)

Max Activating Token Index: 25

Text #3

Max Range: 2.5829. Min Range: -2.5829

Max Act: 2.5601. Min Act: -0.0000

Data Index: 1532862 (Python Code)

Max Activating Token Index: 54

Text #4

Max Range: 2.5829. Min Range: -2.5829

Max Act: 2.5380. Min Act: -0.0000

Data Index: 1518840 (Python Code)

Max Activating Token Index: 15

Text #5

Max Range: 2.5829. Min Range: -2.5829

Max Act: 2.4639. Min Act: -0.0000

Data Index: 1609911 (Python Code)

Max Activating Token Index: 14

Text #6

Max Range: 2.5829. Min Range: -2.5829

Max Act: 2.2965. Min Act: -0.0000

Data Index: 1557580 (Python Code)

Max Activating Token Index: 68

Text #7

Max Range: 2.5829. Min Range: -2.5829

Max Act: 2.3869. Min Act: -0.0000

Data Index: 1393485 (Python Code)

Max Activating Token Index: 887

Text #8

Max Range: 2.5829. Min Range: -2.5829

Max Act: 2.2726. Min Act: -0.0000

Data Index: 1366566 (Python Code)

Max Activating Token Index: 60

Text #9

Max Range: 2.5829. Min Range: -2.5829

Max Act: 2.3860. Min Act: -0.0000

Data Index: 1573557 (Python Code)

Max Activating Token Index: 11

Text #10

Max Range: 2.5829. Min Range: -2.5829

Max Act: 2.2605. Min Act: -0.0000

Data Index: 1598614 (Python Code)

Max Activating Token Index: 18

Text #11

Max Range: 2.5829. Min Range: -2.5829

Max Act: 2.3594. Min Act: -0.0000

Data Index: 1514819 (Python Code)

Max Activating Token Index: 596

Text #12

Max Range: 2.5829. Min Range: -2.5829

Max Act: 2.3254. Min Act: -0.0000

Data Index: 1512900 (Python Code)

Max Activating Token Index: 775

Text #13

Max Range: 2.5829. Min Range: -2.5829

Max Act: 2.2004. Min Act: -0.0000

Data Index: 1441975 (Python Code)

Max Activating Token Index: 8

Text #14

Max Range: 2.5829. Min Range: -2.5829

Max Act: 2.4429. Min Act: -0.0001

Data Index: 1399908 (Python Code)

Max Activating Token Index: 139

Text #15

Max Range: 2.5829. Min Range: -2.5829

Max Act: 2.3154. Min Act: -0.0000

Data Index: 1612092 (Python Code)

Max Activating Token Index: 95

Text #16

Max Range: 2.5829. Min Range: -2.5829

Max Act: 2.3136. Min Act: -0.0000

Data Index: 1453365 (Python Code)

Max Activating Token Index: 59

Text #17

Max Range: 2.5829. Min Range: -2.5829

Max Act: 2.0529. Min Act: -0.0000

Data Index: 1503862 (Python Code)

Max Activating Token Index: 262

Text #18

Max Range: 2.5829. Min Range: -2.5829

Max Act: 2.2886. Min Act: -0.0000

Data Index: 1645017 (Python Code)

Max Activating Token Index: 8

Text #19

Max Range: 2.5829. Min Range: -2.5829

Max Act: 2.4028. Min Act: -0.0000

Data Index: 1535058 (Python Code)

Max Activating Token Index: 87