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

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

Neuron 475 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: 0.5299. Min Range: -0.5299

Max Act: 0.5200. Min Act: -0.0003

Data Index: 622083 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.5299. Min Act: -0.0003

Data Index: 662107 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.5104. Min Act: -0.0002

Data Index: 668760 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4869. Min Act: -0.0002

Data Index: 955036 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4852. Min Act: -0.0003

Data Index: 74404 (C4 (Web Text))

Max Activating Token Index: 401

Text #5

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4701. Min Act: -0.0002

Data Index: 1106514 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.5199. Min Act: -0.0002

Data Index: 564383 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4656. Min Act: -0.0003

Data Index: 466845 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4421. Min Act: -0.0003

Data Index: 567459 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4527. Min Act: -0.0002

Data Index: 496268 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4507. Min Act: -0.0003

Data Index: 806116 (C4 (Web Text))

Max Activating Token Index: 497

Text #11

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4635. Min Act: -0.0003

Data Index: 375820 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4445. Min Act: -0.0003

Data Index: 1314965 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4385. Min Act: -0.0003

Data Index: 1029068 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4307. Min Act: -0.0003

Data Index: 624825 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4289. Min Act: -0.0003

Data Index: 1103577 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4553. Min Act: -0.0003

Data Index: 1265474 (C4 (Web Text))

Max Activating Token Index: 319

Text #17

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4228. Min Act: -0.0003

Data Index: 235724 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4218. Min Act: -0.0003

Data Index: 799177 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 0.5299. Min Range: -0.5299

Max Act: 0.4149. Min Act: -0.0003

Data Index: 200165 (C4 (Web Text))

Max Activating Token Index: 194