Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3291 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0269. Min Range: -1.0269

Max Act: 1.0269. Min Act: -0.0000

Data Index: 658191 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 1.0269. Min Range: -1.0269

Max Act: 0.8233. Min Act: -0.0000

Data Index: 917835 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 1.0269. Min Range: -1.0269

Max Act: 0.7215. Min Act: -0.0000

Data Index: 173964 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 1.0269. Min Range: -1.0269

Max Act: 0.7541. Min Act: -0.0000

Data Index: 820881 (C4 (Web Text))

Max Activating Token Index: 486

Text #4

Max Range: 1.0269. Min Range: -1.0269

Max Act: 0.7812. Min Act: -0.0000

Data Index: 448974 (C4 (Web Text))

Max Activating Token Index: 964

Text #5

Max Range: 1.0269. Min Range: -1.0269

Max Act: 0.6862. Min Act: -0.0000

Data Index: 1201116 (C4 (Web Text))

Max Activating Token Index: 214

Text #6

Max Range: 1.0269. Min Range: -1.0269

Max Act: 0.6485. Min Act: -0.0000

Data Index: 72904 (C4 (Web Text))

Max Activating Token Index: 274

Text #7

Max Range: 1.0269. Min Range: -1.0269

Max Act: 0.6592. Min Act: -0.0000

Data Index: 395537 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 1.0269. Min Range: -1.0269

Max Act: 0.6723. Min Act: -0.0000

Data Index: 488362 (C4 (Web Text))

Max Activating Token Index: 666

Text #9

Max Range: 1.0269. Min Range: -1.0269

Max Act: 0.6217. Min Act: -0.0000

Data Index: 300096 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 1.0269. Min Range: -1.0269

Max Act: 0.6134. Min Act: -0.0000

Data Index: 653917 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 1.0269. Min Range: -1.0269

Max Act: 0.6316. Min Act: -0.0000

Data Index: 675903 (C4 (Web Text))

Max Activating Token Index: 537

Text #12

Max Range: 1.0269. Min Range: -1.0269

Max Act: 0.6356. Min Act: -0.0000

Data Index: 1026169 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 1.0269. Min Range: -1.0269

Max Act: 0.6250. Min Act: -0.0000

Data Index: 527087 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 1.0269. Min Range: -1.0269

Max Act: 0.6263. Min Act: -0.0000

Data Index: 1313155 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 1.0269. Min Range: -1.0269

Max Act: 0.5995. Min Act: -0.0000

Data Index: 522959 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 1.0269. Min Range: -1.0269

Max Act: 0.6145. Min Act: -0.0000

Data Index: 635798 (C4 (Web Text))

Max Activating Token Index: 258

Text #17

Max Range: 1.0269. Min Range: -1.0269

Max Act: 0.5609. Min Act: -0.0000

Data Index: 133162 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 1.0269. Min Range: -1.0269

Max Act: 0.5929. Min Act: -0.0000

Data Index: 683887 (C4 (Web Text))

Max Activating Token Index: 203

Text #19

Max Range: 1.0269. Min Range: -1.0269

Max Act: 0.5902. Min Act: -0.0000

Data Index: 980146 (C4 (Web Text))

Max Activating Token Index: 836