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

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

Neuron 3655 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.7675. Min Act: -0.0001

Data Index: 1489270 (Python Code)

Max Activating Token Index: 1002

Text #1

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.7272. Min Act: -0.0001

Data Index: 1138180 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.6588. Min Act: -0.0001

Data Index: 1479366 (Python Code)

Max Activating Token Index: 928

Text #3

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.6986. Min Act: -0.0001

Data Index: 1411880 (Python Code)

Max Activating Token Index: 6

Text #4

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.6529. Min Act: -0.0001

Data Index: 1480565 (Python Code)

Max Activating Token Index: 10

Text #5

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.6691. Min Act: -0.0001

Data Index: 1393792 (Python Code)

Max Activating Token Index: 17

Text #6

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.6417. Min Act: -0.0002

Data Index: 1398447 (Python Code)

Max Activating Token Index: 30

Text #7

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.6552. Min Act: -0.0001

Data Index: 213381 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.6497. Min Act: -0.0001

Data Index: 1528275 (Python Code)

Max Activating Token Index: 8

Text #9

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.6585. Min Act: -0.0001

Data Index: 1363952 (Python Code)

Max Activating Token Index: 782

Text #10

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.6348. Min Act: -0.0001

Data Index: 1649069 (Python Code)

Max Activating Token Index: 1010

Text #11

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.5758. Min Act: -0.0002

Data Index: 1333357 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.5742. Min Act: -0.0001

Data Index: 667399 (C4 (Web Text))

Max Activating Token Index: 965

Text #13

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.5735. Min Act: -0.0002

Data Index: 938985 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.6081. Min Act: -0.0001

Data Index: 1641648 (Python Code)

Max Activating Token Index: 44

Text #15

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.5820. Min Act: -0.0001

Data Index: 246939 (C4 (Web Text))

Max Activating Token Index: 983

Text #16

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.6002. Min Act: -0.0001

Data Index: 1627841 (Python Code)

Max Activating Token Index: 57

Text #17

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.5782. Min Act: -0.0002

Data Index: 928087 (C4 (Web Text))

Max Activating Token Index: 887

Text #18

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.5673. Min Act: -0.0001

Data Index: 988761 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 0.7675. Min Range: -0.7675

Max Act: 0.5955. Min Act: -0.0001

Data Index: 1141923 (C4 (Web Text))

Max Activating Token Index: 954