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

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

Neuron 4124 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: 1.9281. Min Range: -1.9281

Max Act: 1.9281. Min Act: -0.0000

Data Index: 738597 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.9065. Min Act: -0.0000

Data Index: 654452 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.7338. Min Act: -0.0000

Data Index: 672181 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.7752. Min Act: -0.0000

Data Index: 284139 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.6828. Min Act: -0.0000

Data Index: 1239979 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.7862. Min Act: -0.0000

Data Index: 1315977 (C4 (Web Text))

Max Activating Token Index: 469

Text #6

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.6034. Min Act: -0.0000

Data Index: 242381 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.6797. Min Act: -0.0000

Data Index: 631144 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.6316. Min Act: -0.0000

Data Index: 1093397 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.4708. Min Act: -0.0000

Data Index: 180891 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.6313. Min Act: -0.0000

Data Index: 1142392 (C4 (Web Text))

Max Activating Token Index: 340

Text #11

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.6193. Min Act: -0.0000

Data Index: 1279745 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.5943. Min Act: -0.0000

Data Index: 784308 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.5698. Min Act: -0.0000

Data Index: 339664 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.4401. Min Act: -0.0000

Data Index: 360585 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.4311. Min Act: -0.0000

Data Index: 748504 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.5155. Min Act: -0.0000

Data Index: 21845 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.5059. Min Act: -0.0000

Data Index: 1119160 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.5091. Min Act: -0.0000

Data Index: 941705 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 1.9281. Min Range: -1.9281

Max Act: 1.5940. Min Act: -0.0000

Data Index: 278999 (C4 (Web Text))

Max Activating Token Index: 348