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

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

Neuron 321 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.6373. Min Act: -0.0000

Data Index: 239578 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.6256. Min Act: -0.0000

Data Index: 942134 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.5778. Min Act: -0.0000

Data Index: 1251198 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.5941. Min Act: -0.0000

Data Index: 610906 (C4 (Web Text))

Max Activating Token Index: 554

Text #4

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.5715. Min Act: -0.0000

Data Index: 971928 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.5577. Min Act: -0.0000

Data Index: 354229 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.5210. Min Act: -0.0000

Data Index: 921703 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.5717. Min Act: -0.0000

Data Index: 369259 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.5130. Min Act: -0.0000

Data Index: 212231 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.5334. Min Act: -0.0000

Data Index: 829158 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.5190. Min Act: -0.0000

Data Index: 850702 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.4745. Min Act: -0.0000

Data Index: 577874 (C4 (Web Text))

Max Activating Token Index: 743

Text #12

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.5037. Min Act: -0.0000

Data Index: 1193197 (C4 (Web Text))

Max Activating Token Index: 617

Text #13

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.4830. Min Act: -0.0000

Data Index: 1094429 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.4930. Min Act: -0.0000

Data Index: 179993 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.5077. Min Act: -0.0000

Data Index: 264678 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.4883. Min Act: -0.0000

Data Index: 679718 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.4654. Min Act: -0.0000

Data Index: 268655 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.4845. Min Act: -0.0000

Data Index: 562738 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 0.6373. Min Range: -0.6373

Max Act: 0.4625. Min Act: -0.0000

Data Index: 188304 (C4 (Web Text))

Max Activating Token Index: 481