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

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

Neuron 5443 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: 0.1006. Min Range: -0.1006

Max Act: 0.1006. Min Act: -0.0003

Data Index: 522797 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0976. Min Act: -0.0003

Data Index: 100874 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0959. Min Act: -0.0002

Data Index: 1270815 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0943. Min Act: -0.0002

Data Index: 296512 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0942. Min Act: -0.0002

Data Index: 23897 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0922. Min Act: -0.0002

Data Index: 842844 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0910. Min Act: -0.0002

Data Index: 109773 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0910. Min Act: -0.0002

Data Index: 1301626 (C4 (Web Text))

Max Activating Token Index: 6

Text #8

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0918. Min Act: -0.0002

Data Index: 1356205 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0879. Min Act: -0.0003

Data Index: 36594 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0887. Min Act: -0.0002

Data Index: 844134 (C4 (Web Text))

Max Activating Token Index: 7

Text #11

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0902. Min Act: -0.0003

Data Index: 47450 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0872. Min Act: -0.0002

Data Index: 1075503 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0897. Min Act: -0.0003

Data Index: 423938 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0867. Min Act: -0.0002

Data Index: 441297 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0882. Min Act: -0.0002

Data Index: 171553 (C4 (Web Text))

Max Activating Token Index: 4

Text #16

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0868. Min Act: -0.0002

Data Index: 298419 (C4 (Web Text))

Max Activating Token Index: 67

Text #17

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0867. Min Act: -0.0003

Data Index: 125498 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0846. Min Act: -0.0002

Data Index: 880752 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0847. Min Act: -0.0002

Data Index: 349443 (C4 (Web Text))

Max Activating Token Index: 3