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

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

Neuron 604 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5642. Min Act: -0.0000

Data Index: 1324326 (C4 (Web Text))

Max Activating Token Index: 434

Text #1

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5220. Min Act: -0.0000

Data Index: 1241912 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4879. Min Act: -0.0000

Data Index: 519346 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4484. Min Act: -0.0000

Data Index: 1439791 (Python Code)

Max Activating Token Index: 289

Text #4

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4291. Min Act: -0.0000

Data Index: 1577836 (Python Code)

Max Activating Token Index: 20

Text #5

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4291. Min Act: -0.0000

Data Index: 1463917 (Python Code)

Max Activating Token Index: 20

Text #6

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4074. Min Act: -0.0000

Data Index: 1313621 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4000. Min Act: -0.0000

Data Index: 793858 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4369. Min Act: -0.0000

Data Index: 1493127 (Python Code)

Max Activating Token Index: 17

Text #9

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4369. Min Act: -0.0000

Data Index: 1384237 (Python Code)

Max Activating Token Index: 17

Text #10

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4369. Min Act: -0.0000

Data Index: 1466885 (Python Code)

Max Activating Token Index: 17

Text #11

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4015. Min Act: -0.0000

Data Index: 1560979 (Python Code)

Max Activating Token Index: 166

Text #12

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4239. Min Act: -0.0000

Data Index: 1618678 (Python Code)

Max Activating Token Index: 679

Text #13

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.3599. Min Act: -0.0000

Data Index: 1545951 (Python Code)

Max Activating Token Index: 92

Text #14

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4045. Min Act: -0.0000

Data Index: 943155 (C4 (Web Text))

Max Activating Token Index: 751

Text #15

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4234. Min Act: -0.0000

Data Index: 1640373 (Python Code)

Max Activating Token Index: 789

Text #16

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.3747. Min Act: -0.0000

Data Index: 436069 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.3919. Min Act: -0.0000

Data Index: 1533160 (Python Code)

Max Activating Token Index: 771

Text #18

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.3760. Min Act: -0.0000

Data Index: 334722 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.3922. Min Act: -0.0000

Data Index: 1489607 (Python Code)

Max Activating Token Index: 242