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

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

Neuron 1684 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1134. Min Range: -1.1134

Max Act: 1.1134. Min Act: -0.0000

Data Index: 119305 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 1.1134. Min Range: -1.1134

Max Act: 1.0341. Min Act: -0.0001

Data Index: 1314724 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 1.1134. Min Range: -1.1134

Max Act: 0.8910. Min Act: -0.0000

Data Index: 961296 (C4 (Web Text))

Max Activating Token Index: 639

Text #3

Max Range: 1.1134. Min Range: -1.1134

Max Act: 0.8016. Min Act: -0.0001

Data Index: 984036 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 1.1134. Min Range: -1.1134

Max Act: 0.8354. Min Act: -0.0000

Data Index: 853264 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 1.1134. Min Range: -1.1134

Max Act: 0.8038. Min Act: -0.0000

Data Index: 703458 (C4 (Web Text))

Max Activating Token Index: 568

Text #6

Max Range: 1.1134. Min Range: -1.1134

Max Act: 0.8229. Min Act: -0.0000

Data Index: 109839 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 1.1134. Min Range: -1.1134

Max Act: 0.7697. Min Act: -0.0001

Data Index: 859387 (C4 (Web Text))

Max Activating Token Index: 571

Text #8

Max Range: 1.1134. Min Range: -1.1134

Max Act: 0.7717. Min Act: -0.0001

Data Index: 1210481 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 1.1134. Min Range: -1.1134

Max Act: 0.7539. Min Act: -0.0001

Data Index: 6959 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 1.1134. Min Range: -1.1134

Max Act: 0.7892. Min Act: -0.0000

Data Index: 629606 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 1.1134. Min Range: -1.1134

Max Act: 0.7194. Min Act: -0.0000

Data Index: 698020 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 1.1134. Min Range: -1.1134

Max Act: 0.7315. Min Act: -0.0000

Data Index: 87539 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 1.1134. Min Range: -1.1134

Max Act: 0.7950. Min Act: -0.0000

Data Index: 1040954 (C4 (Web Text))

Max Activating Token Index: 281

Text #14

Max Range: 1.1134. Min Range: -1.1134

Max Act: 0.7378. Min Act: -0.0001

Data Index: 483192 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 1.1134. Min Range: -1.1134

Max Act: 0.7774. Min Act: -0.0000

Data Index: 781514 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 1.1134. Min Range: -1.1134

Max Act: 0.7178. Min Act: -0.0000

Data Index: 635092 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 1.1134. Min Range: -1.1134

Max Act: 0.6667. Min Act: -0.0000

Data Index: 951268 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 1.1134. Min Range: -1.1134

Max Act: 0.7124. Min Act: -0.0001

Data Index: 42390 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 1.1134. Min Range: -1.1134

Max Act: 0.7177. Min Act: -0.0001

Data Index: 597677 (C4 (Web Text))

Max Activating Token Index: 405