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

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

Neuron 1937 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0910. Min Range: -1.0910

Max Act: 1.0910. Min Act: -0.0000

Data Index: 136532 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 1.0910. Min Range: -1.0910

Max Act: 0.8179. Min Act: -0.0000

Data Index: 992123 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 1.0910. Min Range: -1.0910

Max Act: 0.7833. Min Act: -0.0000

Data Index: 1092143 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 1.0910. Min Range: -1.0910

Max Act: 0.7749. Min Act: -0.0000

Data Index: 1302596 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 1.0910. Min Range: -1.0910

Max Act: 0.7190. Min Act: -0.0000

Data Index: 154205 (C4 (Web Text))

Max Activating Token Index: 535

Text #5

Max Range: 1.0910. Min Range: -1.0910

Max Act: 0.6764. Min Act: -0.0000

Data Index: 1298662 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 1.0910. Min Range: -1.0910

Max Act: 0.6670. Min Act: -0.0000

Data Index: 152328 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 1.0910. Min Range: -1.0910

Max Act: 0.6102. Min Act: -0.0000

Data Index: 1141529 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 1.0910. Min Range: -1.0910

Max Act: 0.6462. Min Act: -0.0000

Data Index: 405620 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 1.0910. Min Range: -1.0910

Max Act: 0.5874. Min Act: -0.0000

Data Index: 147893 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 1.0910. Min Range: -1.0910

Max Act: 0.5772. Min Act: -0.0000

Data Index: 665147 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 1.0910. Min Range: -1.0910

Max Act: 0.5503. Min Act: -0.0000

Data Index: 312091 (C4 (Web Text))

Max Activating Token Index: 456

Text #12

Max Range: 1.0910. Min Range: -1.0910

Max Act: 0.5613. Min Act: -0.0000

Data Index: 1307868 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 1.0910. Min Range: -1.0910

Max Act: 0.5393. Min Act: -0.0000

Data Index: 80182 (C4 (Web Text))

Max Activating Token Index: 214

Text #14

Max Range: 1.0910. Min Range: -1.0910

Max Act: 0.5194. Min Act: -0.0000

Data Index: 912386 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 1.0910. Min Range: -1.0910

Max Act: 0.4981. Min Act: -0.0000

Data Index: 446991 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 1.0910. Min Range: -1.0910

Max Act: 0.5107. Min Act: -0.0000

Data Index: 540281 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 1.0910. Min Range: -1.0910

Max Act: 0.5006. Min Act: -0.0000

Data Index: 953401 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 1.0910. Min Range: -1.0910

Max Act: 0.5064. Min Act: -0.0000

Data Index: 747973 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 1.0910. Min Range: -1.0910

Max Act: 0.5006. Min Act: -0.0000

Data Index: 1333939 (C4 (Web Text))

Max Activating Token Index: 870