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

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

Neuron 3290 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.8722. Min Act: -0.0003

Data Index: 425276 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.8237. Min Act: -0.0003

Data Index: 953054 (C4 (Web Text))

Max Activating Token Index: 306

Text #2

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.8151. Min Act: -0.0003

Data Index: 437229 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.7959. Min Act: -0.0003

Data Index: 1073151 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.7886. Min Act: -0.0003

Data Index: 551059 (C4 (Web Text))

Max Activating Token Index: 225

Text #5

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.7018. Min Act: -0.0002

Data Index: 703492 (C4 (Web Text))

Max Activating Token Index: 212

Text #6

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.6228. Min Act: -0.0002

Data Index: 1322680 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.6550. Min Act: -0.0002

Data Index: 634748 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.5798. Min Act: -0.0002

Data Index: 436876 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.5275. Min Act: -0.0002

Data Index: 91297 (C4 (Web Text))

Max Activating Token Index: 244

Text #10

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.5196. Min Act: -0.0002

Data Index: 165159 (C4 (Web Text))

Max Activating Token Index: 492

Text #11

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.5283. Min Act: -0.0003

Data Index: 504639 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.5165. Min Act: -0.0002

Data Index: 1009211 (C4 (Web Text))

Max Activating Token Index: 204

Text #13

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.5297. Min Act: -0.0003

Data Index: 1234376 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.4647. Min Act: -0.0003

Data Index: 1304036 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.5403. Min Act: -0.0002

Data Index: 257776 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.5361. Min Act: -0.0003

Data Index: 787938 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.5366. Min Act: -0.0003

Data Index: 399137 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.5280. Min Act: -0.0002

Data Index: 500182 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.5709. Min Act: -0.0002

Data Index: 844728 (C4 (Web Text))

Max Activating Token Index: 208