Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1668 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.7635. Min Act: -0.0000

Data Index: 1331165 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.7544. Min Act: -0.0000

Data Index: 591714 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.7199. Min Act: -0.0000

Data Index: 976281 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.6603. Min Act: -0.0000

Data Index: 1286027 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.6241. Min Act: -0.0000

Data Index: 356861 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.6088. Min Act: -0.0000

Data Index: 246458 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.6338. Min Act: -0.0000

Data Index: 1283042 (C4 (Web Text))

Max Activating Token Index: 703

Text #7

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.6200. Min Act: -0.0000

Data Index: 1069370 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.6061. Min Act: -0.0000

Data Index: 1178375 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.6257. Min Act: -0.0000

Data Index: 1016852 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5898. Min Act: -0.0000

Data Index: 782736 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5824. Min Act: -0.0000

Data Index: 926234 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.6140. Min Act: -0.0000

Data Index: 763218 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5940. Min Act: -0.0000

Data Index: 705690 (C4 (Web Text))

Max Activating Token Index: 479

Text #14

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5832. Min Act: -0.0000

Data Index: 1172728 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5991. Min Act: -0.0000

Data Index: 1313500 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.6013. Min Act: -0.0000

Data Index: 777455 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5987. Min Act: -0.0000

Data Index: 1025874 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5671. Min Act: -0.0000

Data Index: 708997 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 0.7635. Min Range: -0.7635

Max Act: 0.5668. Min Act: -0.0000

Data Index: 178426 (C4 (Web Text))

Max Activating Token Index: 607