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

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

Neuron 2015 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0127. Min Range: -4.0127

Max Act: 4.0127. Min Act: -0.0000

Data Index: 1346480 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 4.0127. Min Range: -4.0127

Max Act: 3.5005. Min Act: -0.0000

Data Index: 332764 (C4 (Web Text))

Max Activating Token Index: 488

Text #2

Max Range: 4.0127. Min Range: -4.0127

Max Act: 3.4153. Min Act: -0.0000

Data Index: 928522 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 4.0127. Min Range: -4.0127

Max Act: 3.3343. Min Act: -0.0000

Data Index: 155011 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 4.0127. Min Range: -4.0127

Max Act: 3.0166. Min Act: -0.0000

Data Index: 183426 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 4.0127. Min Range: -4.0127

Max Act: 3.0230. Min Act: -0.0000

Data Index: 155278 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 4.0127. Min Range: -4.0127

Max Act: 3.0146. Min Act: -0.0000

Data Index: 1147527 (C4 (Web Text))

Max Activating Token Index: 211

Text #7

Max Range: 4.0127. Min Range: -4.0127

Max Act: 2.9179. Min Act: -0.0000

Data Index: 311565 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 4.0127. Min Range: -4.0127

Max Act: 2.8819. Min Act: -0.0000

Data Index: 680472 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 4.0127. Min Range: -4.0127

Max Act: 2.5999. Min Act: -0.0000

Data Index: 1188952 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 4.0127. Min Range: -4.0127

Max Act: 2.8512. Min Act: -0.0000

Data Index: 932889 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 4.0127. Min Range: -4.0127

Max Act: 2.5675. Min Act: -0.0000

Data Index: 1035714 (C4 (Web Text))

Max Activating Token Index: 948

Text #12

Max Range: 4.0127. Min Range: -4.0127

Max Act: 2.5933. Min Act: -0.0000

Data Index: 112898 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 4.0127. Min Range: -4.0127

Max Act: 2.9935. Min Act: -0.0000

Data Index: 274926 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 4.0127. Min Range: -4.0127

Max Act: 2.8274. Min Act: -0.0000

Data Index: 1002876 (C4 (Web Text))

Max Activating Token Index: 612

Text #15

Max Range: 4.0127. Min Range: -4.0127

Max Act: 2.7782. Min Act: -0.0000

Data Index: 865903 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 4.0127. Min Range: -4.0127

Max Act: 2.6663. Min Act: -0.0000

Data Index: 1061810 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 4.0127. Min Range: -4.0127

Max Act: 2.7666. Min Act: -0.0000

Data Index: 272459 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 4.0127. Min Range: -4.0127

Max Act: 2.6277. Min Act: -0.0000

Data Index: 385082 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 4.0127. Min Range: -4.0127

Max Act: 2.7175. Min Act: -0.0000

Data Index: 421133 (C4 (Web Text))

Max Activating Token Index: 554