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

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

Neuron 490 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: 1.1108. Min Range: -1.1108

Max Act: 1.1108. Min Act: -0.0001

Data Index: 953483 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 1.1108. Min Range: -1.1108

Max Act: 0.9141. Min Act: -0.0001

Data Index: 1468652 (Python Code)

Max Activating Token Index: 77

Text #2

Max Range: 1.1108. Min Range: -1.1108

Max Act: 0.8833. Min Act: -0.0001

Data Index: 1291248 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 1.1108. Min Range: -1.1108

Max Act: 0.8684. Min Act: -0.0001

Data Index: 1083621 (C4 (Web Text))

Max Activating Token Index: 481

Text #4

Max Range: 1.1108. Min Range: -1.1108

Max Act: 0.7760. Min Act: -0.0001

Data Index: 1224480 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 1.1108. Min Range: -1.1108

Max Act: 0.7895. Min Act: -0.0001

Data Index: 660164 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 1.1108. Min Range: -1.1108

Max Act: 0.8185. Min Act: -0.0001

Data Index: 415591 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 1.1108. Min Range: -1.1108

Max Act: 0.8390. Min Act: -0.0001

Data Index: 1074969 (C4 (Web Text))

Max Activating Token Index: 580

Text #8

Max Range: 1.1108. Min Range: -1.1108

Max Act: 0.7710. Min Act: -0.0001

Data Index: 1452731 (Python Code)

Max Activating Token Index: 843

Text #9

Max Range: 1.1108. Min Range: -1.1108

Max Act: 0.7404. Min Act: -0.0001

Data Index: 1442913 (Python Code)

Max Activating Token Index: 551

Text #10

Max Range: 1.1108. Min Range: -1.1108

Max Act: 0.7505. Min Act: -0.0001

Data Index: 1634353 (Python Code)

Max Activating Token Index: 795

Text #11

Max Range: 1.1108. Min Range: -1.1108

Max Act: 0.7251. Min Act: -0.0001

Data Index: 1481053 (Python Code)

Max Activating Token Index: 437

Text #12

Max Range: 1.1108. Min Range: -1.1108

Max Act: 0.7143. Min Act: -0.0001

Data Index: 1649131 (Python Code)

Max Activating Token Index: 80

Text #13

Max Range: 1.1108. Min Range: -1.1108

Max Act: 0.7373. Min Act: -0.0001

Data Index: 1372431 (Python Code)

Max Activating Token Index: 954

Text #14

Max Range: 1.1108. Min Range: -1.1108

Max Act: 0.7582. Min Act: -0.0001

Data Index: 1484041 (Python Code)

Max Activating Token Index: 936

Text #15

Max Range: 1.1108. Min Range: -1.1108

Max Act: 0.7481. Min Act: -0.0001

Data Index: 776313 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 1.1108. Min Range: -1.1108

Max Act: 0.7311. Min Act: -0.0001

Data Index: 1554228 (Python Code)

Max Activating Token Index: 175

Text #17

Max Range: 1.1108. Min Range: -1.1108

Max Act: 0.7029. Min Act: -0.0001

Data Index: 1474614 (Python Code)

Max Activating Token Index: 65

Text #18

Max Range: 1.1108. Min Range: -1.1108

Max Act: 0.6976. Min Act: -0.0001

Data Index: 1473752 (Python Code)

Max Activating Token Index: 20

Text #19

Max Range: 1.1108. Min Range: -1.1108

Max Act: 0.7402. Min Act: -0.0001

Data Index: 1421581 (Python Code)

Max Activating Token Index: 726