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

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

Neuron 670 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: 0.0003. Min Range: -0.0003

Max Act: 0.0003. Min Act: -0.0002

Data Index: 865904 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0003. Min Act: -0.0002

Data Index: 975390 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 442423 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 774621 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 244681 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1284783 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 93398 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 85654 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1627184 (Python Code)

Max Activating Token Index: 88

Text #9

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1219250 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 605617 (C4 (Web Text))

Max Activating Token Index: 1021

Text #11

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 171078 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1048352 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 406097 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 279000 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1051780 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 153585 (C4 (Web Text))

Max Activating Token Index: 35

Text #17

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1254570 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 546306 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0001

Data Index: 1471023 (Python Code)

Max Activating Token Index: 987