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

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

Neuron 2792 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0315. Min Act: -0.0004

Data Index: 109782 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0283. Min Act: -0.0004

Data Index: 1247347 (C4 (Web Text))

Max Activating Token Index: 935

Text #2

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0278. Min Act: -0.0004

Data Index: 408347 (C4 (Web Text))

Max Activating Token Index: 729

Text #3

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0280. Min Act: -0.0004

Data Index: 192372 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0268. Min Act: -0.0004

Data Index: 252529 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0243. Min Act: -0.0004

Data Index: 208785 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0260. Min Act: -0.0004

Data Index: 1097969 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0265. Min Act: -0.0004

Data Index: 501319 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0277. Min Act: -0.0004

Data Index: 502829 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0270. Min Act: -0.0004

Data Index: 553969 (C4 (Web Text))

Max Activating Token Index: 612

Text #10

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0270. Min Act: -0.0004

Data Index: 1103930 (C4 (Web Text))

Max Activating Token Index: 722

Text #11

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0271. Min Act: -0.0004

Data Index: 394710 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0250. Min Act: -0.0004

Data Index: 1124633 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0263. Min Act: -0.0004

Data Index: 744474 (C4 (Web Text))

Max Activating Token Index: 1003

Text #14

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0252. Min Act: -0.0004

Data Index: 1155125 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0247. Min Act: -0.0004

Data Index: 1315534 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0243. Min Act: -0.0004

Data Index: 1436006 (Python Code)

Max Activating Token Index: 911

Text #17

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0245. Min Act: -0.0004

Data Index: 667356 (C4 (Web Text))

Max Activating Token Index: 820

Text #18

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0267. Min Act: -0.0004

Data Index: 1302183 (C4 (Web Text))

Max Activating Token Index: 678

Text #19

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0247. Min Act: -0.0004

Data Index: 592820 (C4 (Web Text))

Max Activating Token Index: 681