Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 433 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0270. Min Act: -0.0006

Data Index: 1255572 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0280. Min Act: -0.0006

Data Index: 586793 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0270. Min Act: -0.0006

Data Index: 49732 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0274. Min Act: -0.0006

Data Index: 497757 (C4 (Web Text))

Max Activating Token Index: 637

Text #4

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0269. Min Act: -0.0006

Data Index: 103906 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0274. Min Act: -0.0006

Data Index: 854051 (C4 (Web Text))

Max Activating Token Index: 398

Text #6

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0252. Min Act: -0.0006

Data Index: 913280 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0251. Min Act: -0.0006

Data Index: 176478 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0267. Min Act: -0.0006

Data Index: 1277864 (C4 (Web Text))

Max Activating Token Index: 436

Text #9

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0241. Min Act: -0.0006

Data Index: 1163068 (C4 (Web Text))

Max Activating Token Index: 815

Text #10

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0258. Min Act: -0.0006

Data Index: 653014 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0237. Min Act: -0.0006

Data Index: 347956 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0246. Min Act: -0.0006

Data Index: 311310 (C4 (Web Text))

Max Activating Token Index: 401

Text #13

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0243. Min Act: -0.0006

Data Index: 1170734 (C4 (Web Text))

Max Activating Token Index: 627

Text #14

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0259. Min Act: -0.0006

Data Index: 1091901 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0243. Min Act: -0.0006

Data Index: 1287347 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0251. Min Act: -0.0006

Data Index: 560630 (C4 (Web Text))

Max Activating Token Index: 741

Text #17

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0237. Min Act: -0.0006

Data Index: 129459 (C4 (Web Text))

Max Activating Token Index: 337

Text #18

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0248. Min Act: -0.0006

Data Index: 77531 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0242. Min Act: -0.0006

Data Index: 1067479 (C4 (Web Text))

Max Activating Token Index: 429