Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 696 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0352. Min Act: -0.0000

Data Index: 298884 (C4 (Web Text))

Max Activating Token Index: 234

Text #1

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0333. Min Act: -0.0002

Data Index: 58964 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0320. Min Act: -0.0002

Data Index: 901871 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0315. Min Act: -0.0004

Data Index: 1021711 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0287. Min Act: -0.0002

Data Index: 945259 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0281. Min Act: -0.0002

Data Index: 1173157 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0286. Min Act: -0.0002

Data Index: 834396 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0278. Min Act: -0.0000

Data Index: 128096 (C4 (Web Text))

Max Activating Token Index: 866

Text #8

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0282. Min Act: -0.0002

Data Index: 951500 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0276. Min Act: -0.0002

Data Index: 643282 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0274. Min Act: -0.0002

Data Index: 522631 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0277. Min Act: -0.0002

Data Index: 794546 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0277. Min Act: -0.0002

Data Index: 1162213 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0271. Min Act: 0.0002

Data Index: 31443 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0277. Min Act: -0.0003

Data Index: 618900 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0270. Min Act: -0.0003

Data Index: 346432 (C4 (Web Text))

Max Activating Token Index: 295

Text #16

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0274. Min Act: -0.0002

Data Index: 1106546 (C4 (Web Text))

Max Activating Token Index: 937

Text #17

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0267. Min Act: -0.0002

Data Index: 662828 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0269. Min Act: -0.0002

Data Index: 1172925 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 0.0352. Min Range: -0.0352

Max Act: 0.0268. Min Act: -0.0003

Data Index: 789199 (C4 (Web Text))

Max Activating Token Index: 450