Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2887 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0357. Min Act: -0.0002

Data Index: 733953 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0328. Min Act: -0.0003

Data Index: 585628 (C4 (Web Text))

Max Activating Token Index: 935

Text #2

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0311. Min Act: -0.0003

Data Index: 225938 (C4 (Web Text))

Max Activating Token Index: 823

Text #3

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0310. Min Act: -0.0003

Data Index: 943522 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1495475 (Python Code)

Max Activating Token Index: 221

Text #5

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0300. Min Act: -0.0003

Data Index: 915309 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0297. Min Act: -0.0003

Data Index: 275237 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0297. Min Act: -0.0002

Data Index: 897217 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0293. Min Act: -0.0003

Data Index: 1251055 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0295. Min Act: -0.0003

Data Index: 1294543 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0290. Min Act: -0.0003

Data Index: 533460 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0288. Min Act: -0.0002

Data Index: 1088284 (C4 (Web Text))

Max Activating Token Index: 378

Text #12

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0280. Min Act: -0.0002

Data Index: 803128 (C4 (Web Text))

Max Activating Token Index: 555

Text #13

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0279. Min Act: -0.0003

Data Index: 1536494 (Python Code)

Max Activating Token Index: 628

Text #14

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0283. Min Act: -0.0003

Data Index: 438720 (C4 (Web Text))

Max Activating Token Index: 723

Text #15

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0272. Min Act: -0.0003

Data Index: 495040 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0266. Min Act: -0.0003

Data Index: 195218 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0265. Min Act: -0.0003

Data Index: 1066834 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0264. Min Act: -0.0003

Data Index: 103751 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0262. Min Act: -0.0003

Data Index: 1091625 (C4 (Web Text))

Max Activating Token Index: 480