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

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

Neuron 2468 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: 0.8776. Min Range: -0.8776

Max Act: 0.8776. Min Act: -0.0002

Data Index: 469757 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 0.8776. Min Range: -0.8776

Max Act: 0.8657. Min Act: -0.0002

Data Index: 1057147 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 0.8776. Min Range: -0.8776

Max Act: 0.8416. Min Act: -0.0002

Data Index: 237817 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 0.8776. Min Range: -0.8776

Max Act: 0.8267. Min Act: -0.0002

Data Index: 352769 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 0.8776. Min Range: -0.8776

Max Act: 0.8318. Min Act: -0.0002

Data Index: 58581 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 0.8776. Min Range: -0.8776

Max Act: 0.8196. Min Act: -0.0002

Data Index: 1024898 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 0.8776. Min Range: -0.8776

Max Act: 0.8099. Min Act: -0.0002

Data Index: 704856 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 0.8776. Min Range: -0.8776

Max Act: 0.8374. Min Act: -0.0002

Data Index: 1171711 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 0.8776. Min Range: -0.8776

Max Act: 0.8319. Min Act: -0.0002

Data Index: 1321339 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 0.8776. Min Range: -0.8776

Max Act: 0.8073. Min Act: -0.0002

Data Index: 523566 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 0.8776. Min Range: -0.8776

Max Act: 0.8132. Min Act: -0.0002

Data Index: 1347429 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 0.8776. Min Range: -0.8776

Max Act: 0.8160. Min Act: -0.0002

Data Index: 611321 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 0.8776. Min Range: -0.8776

Max Act: 0.7911. Min Act: -0.0002

Data Index: 63899 (C4 (Web Text))

Max Activating Token Index: 5

Text #13

Max Range: 0.8776. Min Range: -0.8776

Max Act: 0.8087. Min Act: -0.0002

Data Index: 1214998 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 0.8776. Min Range: -0.8776

Max Act: 0.8019. Min Act: -0.0002

Data Index: 177852 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 0.8776. Min Range: -0.8776

Max Act: 0.7912. Min Act: -0.0003

Data Index: 457330 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 0.8776. Min Range: -0.8776

Max Act: 0.7847. Min Act: -0.0002

Data Index: 1145662 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 0.8776. Min Range: -0.8776

Max Act: 0.8052. Min Act: -0.0002

Data Index: 109261 (C4 (Web Text))

Max Activating Token Index: 131

Text #18

Max Range: 0.8776. Min Range: -0.8776

Max Act: 0.8015. Min Act: -0.0002

Data Index: 279589 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 0.8776. Min Range: -0.8776

Max Act: 0.7950. Min Act: -0.0002

Data Index: 916474 (C4 (Web Text))

Max Activating Token Index: 33