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

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

Neuron 865 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0391. Min Act: -0.0004

Data Index: 924195 (C4 (Web Text))

Max Activating Token Index: 658

Text #1

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0393. Min Act: -0.0004

Data Index: 62158 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0343. Min Act: -0.0004

Data Index: 635007 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0316. Min Act: -0.0004

Data Index: 1059001 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0334. Min Act: -0.0004

Data Index: 57902 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0315. Min Act: -0.0004

Data Index: 627732 (C4 (Web Text))

Max Activating Token Index: 602

Text #6

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0326. Min Act: -0.0004

Data Index: 641536 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0332. Min Act: -0.0004

Data Index: 1004937 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0332. Min Act: -0.0004

Data Index: 318357 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0343. Min Act: -0.0004

Data Index: 493715 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0342. Min Act: -0.0004

Data Index: 1006505 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0298. Min Act: -0.0004

Data Index: 444419 (C4 (Web Text))

Max Activating Token Index: 685

Text #12

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0326. Min Act: -0.0004

Data Index: 759852 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0302. Min Act: -0.0004

Data Index: 835995 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0299. Min Act: -0.0004

Data Index: 433293 (C4 (Web Text))

Max Activating Token Index: 721

Text #15

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0300. Min Act: -0.0004

Data Index: 417580 (C4 (Web Text))

Max Activating Token Index: 685

Text #16

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0305. Min Act: -0.0004

Data Index: 891414 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0294. Min Act: -0.0004

Data Index: 493865 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0285. Min Act: -0.0004

Data Index: 239686 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0320. Min Act: -0.0004

Data Index: 923461 (C4 (Web Text))

Max Activating Token Index: 41