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

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

Neuron 649 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: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0003

Data Index: 1345797 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 779995 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1281233 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0003

Data Index: 949786 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 173008 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 765222 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1167532 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 648926 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 156422 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0003

Data Index: 991851 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1327948 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1331450 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 920294 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1143579 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 674328 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1104467 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 653047 (C4 (Web Text))

Max Activating Token Index: 30

Text #17

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1154964 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 27840 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1270365 (C4 (Web Text))

Max Activating Token Index: 76