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

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

Neuron 4283 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.5759. Min Range: -1.5759

Max Act: 1.5759. Min Act: -0.0002

Data Index: 1587466 (Python Code)

Max Activating Token Index: 4

Text #1

Max Range: 1.5759. Min Range: -1.5759

Max Act: 1.5096. Min Act: -0.0002

Data Index: 1452996 (Python Code)

Max Activating Token Index: 5

Text #2

Max Range: 1.5759. Min Range: -1.5759

Max Act: 1.5124. Min Act: -0.0002

Data Index: 1656474 (Python Code)

Max Activating Token Index: 4

Text #3

Max Range: 1.5759. Min Range: -1.5759

Max Act: 1.4715. Min Act: -0.0002

Data Index: 1442872 (Python Code)

Max Activating Token Index: 4

Text #4

Max Range: 1.5759. Min Range: -1.5759

Max Act: 1.4604. Min Act: -0.0002

Data Index: 1450032 (Python Code)

Max Activating Token Index: 10

Text #5

Max Range: 1.5759. Min Range: -1.5759

Max Act: 1.4510. Min Act: -0.0002

Data Index: 1506676 (Python Code)

Max Activating Token Index: 13

Text #6

Max Range: 1.5759. Min Range: -1.5759

Max Act: 1.4511. Min Act: -0.0002

Data Index: 1576624 (Python Code)

Max Activating Token Index: 13

Text #7

Max Range: 1.5759. Min Range: -1.5759

Max Act: 1.4578. Min Act: -0.0002

Data Index: 1429066 (Python Code)

Max Activating Token Index: 54

Text #8

Max Range: 1.5759. Min Range: -1.5759

Max Act: 1.4239. Min Act: -0.0002

Data Index: 1408891 (Python Code)

Max Activating Token Index: 6

Text #9

Max Range: 1.5759. Min Range: -1.5759

Max Act: 1.4417. Min Act: -0.0002

Data Index: 1435016 (Python Code)

Max Activating Token Index: 6

Text #10

Max Range: 1.5759. Min Range: -1.5759

Max Act: 1.4246. Min Act: -0.0002

Data Index: 1377219 (Python Code)

Max Activating Token Index: 6

Text #11

Max Range: 1.5759. Min Range: -1.5759

Max Act: 1.3933. Min Act: -0.0002

Data Index: 1396227 (Python Code)

Max Activating Token Index: 31

Text #12

Max Range: 1.5759. Min Range: -1.5759

Max Act: 1.4222. Min Act: -0.0002

Data Index: 1540017 (Python Code)

Max Activating Token Index: 7

Text #13

Max Range: 1.5759. Min Range: -1.5759

Max Act: 1.4229. Min Act: -0.0002

Data Index: 1560983 (Python Code)

Max Activating Token Index: 21

Text #14

Max Range: 1.5759. Min Range: -1.5759

Max Act: 1.3948. Min Act: -0.0002

Data Index: 1655955 (Python Code)

Max Activating Token Index: 9

Text #15

Max Range: 1.5759. Min Range: -1.5759

Max Act: 1.4228. Min Act: -0.0002

Data Index: 1624276 (Python Code)

Max Activating Token Index: 11

Text #16

Max Range: 1.5759. Min Range: -1.5759

Max Act: 1.4255. Min Act: -0.0002

Data Index: 1646053 (Python Code)

Max Activating Token Index: 39

Text #17

Max Range: 1.5759. Min Range: -1.5759

Max Act: 1.4245. Min Act: -0.0002

Data Index: 1640678 (Python Code)

Max Activating Token Index: 35

Text #18

Max Range: 1.5759. Min Range: -1.5759

Max Act: 1.4025. Min Act: -0.0002

Data Index: 1397093 (Python Code)

Max Activating Token Index: 30

Text #19

Max Range: 1.5759. Min Range: -1.5759

Max Act: 1.3909. Min Act: -0.0002

Data Index: 1428053 (Python Code)

Max Activating Token Index: 22