Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3714 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9011. Min Range: -0.9011

Max Act: 0.9011. Min Act: -0.0001

Data Index: 241450 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 0.9011. Min Range: -0.9011

Max Act: 0.8635. Min Act: -0.0000

Data Index: 1295832 (C4 (Web Text))

Max Activating Token Index: 306

Text #2

Max Range: 0.9011. Min Range: -0.9011

Max Act: 0.8027. Min Act: -0.0000

Data Index: 748322 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 0.9011. Min Range: -0.9011

Max Act: 0.7784. Min Act: -0.0001

Data Index: 1104358 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 0.9011. Min Range: -0.9011

Max Act: 0.7990. Min Act: -0.0001

Data Index: 52941 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 0.9011. Min Range: -0.9011

Max Act: 0.7536. Min Act: -0.0001

Data Index: 473584 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 0.9011. Min Range: -0.9011

Max Act: 0.8053. Min Act: -0.0001

Data Index: 719902 (C4 (Web Text))

Max Activating Token Index: 801

Text #7

Max Range: 0.9011. Min Range: -0.9011

Max Act: 0.7793. Min Act: -0.0001

Data Index: 859765 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 0.9011. Min Range: -0.9011

Max Act: 0.7352. Min Act: -0.0001

Data Index: 854021 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 0.9011. Min Range: -0.9011

Max Act: 0.7752. Min Act: -0.0000

Data Index: 258343 (C4 (Web Text))

Max Activating Token Index: 797

Text #10

Max Range: 0.9011. Min Range: -0.9011

Max Act: 0.7698. Min Act: -0.0000

Data Index: 136629 (C4 (Web Text))

Max Activating Token Index: 249

Text #11

Max Range: 0.9011. Min Range: -0.9011

Max Act: 0.7312. Min Act: -0.0000

Data Index: 406867 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 0.9011. Min Range: -0.9011

Max Act: 0.7242. Min Act: -0.0000

Data Index: 683004 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 0.9011. Min Range: -0.9011

Max Act: 0.7274. Min Act: -0.0001

Data Index: 323657 (C4 (Web Text))

Max Activating Token Index: 242

Text #14

Max Range: 0.9011. Min Range: -0.9011

Max Act: 0.7104. Min Act: -0.0001

Data Index: 845267 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 0.9011. Min Range: -0.9011

Max Act: 0.5121. Min Act: -0.0000

Data Index: 1151913 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 0.9011. Min Range: -0.9011

Max Act: 0.6992. Min Act: -0.0000

Data Index: 972609 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 0.9011. Min Range: -0.9011

Max Act: 0.6826. Min Act: -0.0001

Data Index: 612050 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 0.9011. Min Range: -0.9011

Max Act: 0.6550. Min Act: -0.0000

Data Index: 998498 (C4 (Web Text))

Max Activating Token Index: 211

Text #19

Max Range: 0.9011. Min Range: -0.9011

Max Act: 0.6762. Min Act: -0.0000

Data Index: 448885 (C4 (Web Text))

Max Activating Token Index: 714