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

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

Neuron 1159 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5999. Min Range: -2.5999

Max Act: 2.5999. Min Act: -0.0000

Data Index: 589525 (C4 (Web Text))

Max Activating Token Index: 807

Text #1

Max Range: 2.5999. Min Range: -2.5999

Max Act: 2.4292. Min Act: -0.0000

Data Index: 768399 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 2.5999. Min Range: -2.5999

Max Act: 2.3671. Min Act: -0.0000

Data Index: 12863 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 2.5999. Min Range: -2.5999

Max Act: 2.2710. Min Act: -0.0000

Data Index: 285865 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 2.5999. Min Range: -2.5999

Max Act: 2.1284. Min Act: -0.0000

Data Index: 825134 (C4 (Web Text))

Max Activating Token Index: 297

Text #5

Max Range: 2.5999. Min Range: -2.5999

Max Act: 2.1010. Min Act: -0.0000

Data Index: 775501 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 2.5999. Min Range: -2.5999

Max Act: 2.0880. Min Act: -0.0000

Data Index: 259810 (C4 (Web Text))

Max Activating Token Index: 391

Text #7

Max Range: 2.5999. Min Range: -2.5999

Max Act: 2.0752. Min Act: -0.0000

Data Index: 222745 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 2.5999. Min Range: -2.5999

Max Act: 2.0408. Min Act: -0.0000

Data Index: 748470 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 2.5999. Min Range: -2.5999

Max Act: 2.0035. Min Act: -0.0000

Data Index: 711176 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 2.5999. Min Range: -2.5999

Max Act: 1.9868. Min Act: -0.0000

Data Index: 806233 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 2.5999. Min Range: -2.5999

Max Act: 1.9483. Min Act: -0.0000

Data Index: 1277927 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 2.5999. Min Range: -2.5999

Max Act: 1.9329. Min Act: -0.0000

Data Index: 639980 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 2.5999. Min Range: -2.5999

Max Act: 1.9353. Min Act: -0.0000

Data Index: 285233 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 2.5999. Min Range: -2.5999

Max Act: 1.8923. Min Act: -0.0000

Data Index: 552870 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 2.5999. Min Range: -2.5999

Max Act: 1.8987. Min Act: -0.0000

Data Index: 278666 (C4 (Web Text))

Max Activating Token Index: 859

Text #16

Max Range: 2.5999. Min Range: -2.5999

Max Act: 1.7956. Min Act: -0.0000

Data Index: 831073 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 2.5999. Min Range: -2.5999

Max Act: 1.8770. Min Act: -0.0000

Data Index: 1540995 (Python Code)

Max Activating Token Index: 116

Text #18

Max Range: 2.5999. Min Range: -2.5999

Max Act: 1.8841. Min Act: -0.0000

Data Index: 465246 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 2.5999. Min Range: -2.5999

Max Act: 1.8783. Min Act: -0.0000

Data Index: 1086470 (C4 (Web Text))

Max Activating Token Index: 606