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

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

Neuron 815 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4334. Min Range: -0.4334

Max Act: 0.4334. Min Act: -0.0001

Data Index: 469383 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 0.4334. Min Range: -0.4334

Max Act: 0.3651. Min Act: -0.0001

Data Index: 172392 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 0.4334. Min Range: -0.4334

Max Act: 0.3454. Min Act: -0.0001

Data Index: 294705 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 0.4334. Min Range: -0.4334

Max Act: 0.3437. Min Act: -0.0001

Data Index: 1063729 (C4 (Web Text))

Max Activating Token Index: 434

Text #4

Max Range: 0.4334. Min Range: -0.4334

Max Act: 0.3379. Min Act: -0.0001

Data Index: 895162 (C4 (Web Text))

Max Activating Token Index: 872

Text #5

Max Range: 0.4334. Min Range: -0.4334

Max Act: 0.3485. Min Act: -0.0001

Data Index: 229775 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 0.4334. Min Range: -0.4334

Max Act: 0.2840. Min Act: -0.0001

Data Index: 830798 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 0.4334. Min Range: -0.4334

Max Act: 0.3355. Min Act: -0.0001

Data Index: 454597 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 0.4334. Min Range: -0.4334

Max Act: 0.3209. Min Act: -0.0001

Data Index: 983440 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 0.4334. Min Range: -0.4334

Max Act: 0.3202. Min Act: -0.0001

Data Index: 838694 (C4 (Web Text))

Max Activating Token Index: 348

Text #10

Max Range: 0.4334. Min Range: -0.4334

Max Act: 0.3242. Min Act: -0.0001

Data Index: 45016 (C4 (Web Text))

Max Activating Token Index: 292

Text #11

Max Range: 0.4334. Min Range: -0.4334

Max Act: 0.3306. Min Act: -0.0001

Data Index: 70005 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 0.4334. Min Range: -0.4334

Max Act: 0.3294. Min Act: -0.0001

Data Index: 814648 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 0.4334. Min Range: -0.4334

Max Act: 0.2859. Min Act: -0.0001

Data Index: 581221 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 0.4334. Min Range: -0.4334

Max Act: 0.3152. Min Act: -0.0001

Data Index: 1315567 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 0.4334. Min Range: -0.4334

Max Act: 0.3231. Min Act: -0.0001

Data Index: 1184352 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 0.4334. Min Range: -0.4334

Max Act: 0.3201. Min Act: -0.0001

Data Index: 464399 (C4 (Web Text))

Max Activating Token Index: 877

Text #17

Max Range: 0.4334. Min Range: -0.4334

Max Act: 0.3209. Min Act: -0.0001

Data Index: 1232923 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 0.4334. Min Range: -0.4334

Max Act: 0.3031. Min Act: -0.0001

Data Index: 612865 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 0.4334. Min Range: -0.4334

Max Act: 0.3091. Min Act: -0.0001

Data Index: 579668 (C4 (Web Text))

Max Activating Token Index: 352