Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2105 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6664. Min Range: -0.6664

Max Act: 0.6664. Min Act: -0.0003

Data Index: 131 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 0.6664. Min Range: -0.6664

Max Act: 0.6216. Min Act: -0.0003

Data Index: 699136 (C4 (Web Text))

Max Activating Token Index: 385

Text #2

Max Range: 0.6664. Min Range: -0.6664

Max Act: 0.5687. Min Act: -0.0003

Data Index: 881513 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 0.6664. Min Range: -0.6664

Max Act: 0.6002. Min Act: -0.0003

Data Index: 92425 (C4 (Web Text))

Max Activating Token Index: 391

Text #4

Max Range: 0.6664. Min Range: -0.6664

Max Act: 0.5393. Min Act: -0.0003

Data Index: 149544 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 0.6664. Min Range: -0.6664

Max Act: 0.5288. Min Act: -0.0003

Data Index: 980379 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 0.6664. Min Range: -0.6664

Max Act: 0.5260. Min Act: -0.0003

Data Index: 784277 (C4 (Web Text))

Max Activating Token Index: 275

Text #7

Max Range: 0.6664. Min Range: -0.6664

Max Act: 0.5207. Min Act: -0.0003

Data Index: 814210 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 0.6664. Min Range: -0.6664

Max Act: 0.5000. Min Act: -0.0003

Data Index: 674731 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 0.6664. Min Range: -0.6664

Max Act: 0.5291. Min Act: -0.0003

Data Index: 547504 (C4 (Web Text))

Max Activating Token Index: 767

Text #10

Max Range: 0.6664. Min Range: -0.6664

Max Act: 0.5179. Min Act: -0.0003

Data Index: 493616 (C4 (Web Text))

Max Activating Token Index: 657

Text #11

Max Range: 0.6664. Min Range: -0.6664

Max Act: 0.5155. Min Act: -0.0003

Data Index: 214206 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 0.6664. Min Range: -0.6664

Max Act: 0.5257. Min Act: -0.0003

Data Index: 61328 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 0.6664. Min Range: -0.6664

Max Act: 0.4947. Min Act: -0.0003

Data Index: 228935 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 0.6664. Min Range: -0.6664

Max Act: 0.4681. Min Act: -0.0003

Data Index: 389380 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 0.6664. Min Range: -0.6664

Max Act: 0.5117. Min Act: -0.0003

Data Index: 1306550 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 0.6664. Min Range: -0.6664

Max Act: 0.4912. Min Act: -0.0003

Data Index: 1022022 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 0.6664. Min Range: -0.6664

Max Act: 0.5036. Min Act: -0.0003

Data Index: 744416 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 0.6664. Min Range: -0.6664

Max Act: 0.4836. Min Act: -0.0003

Data Index: 964991 (C4 (Web Text))

Max Activating Token Index: 855

Text #19

Max Range: 0.6664. Min Range: -0.6664

Max Act: 0.4931. Min Act: -0.0003

Data Index: 16645 (C4 (Web Text))

Max Activating Token Index: 848