Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3976 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1554. Min Act: -0.0001

Data Index: 952612 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1499. Min Act: -0.0002

Data Index: 1099519 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1558. Min Act: -0.0001

Data Index: 456999 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1459. Min Act: -0.0002

Data Index: 122322 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1360. Min Act: -0.0001

Data Index: 1034873 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1450. Min Act: -0.0001

Data Index: 42446 (C4 (Web Text))

Max Activating Token Index: 464

Text #6

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1372. Min Act: -0.0002

Data Index: 104802 (C4 (Web Text))

Max Activating Token Index: 976

Text #7

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1355. Min Act: -0.0002

Data Index: 1290455 (C4 (Web Text))

Max Activating Token Index: 1004

Text #8

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1355. Min Act: -0.0001

Data Index: 1302975 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1348. Min Act: -0.0002

Data Index: 962876 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1310. Min Act: -0.0001

Data Index: 579357 (C4 (Web Text))

Max Activating Token Index: 439

Text #11

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1302. Min Act: -0.0002

Data Index: 446188 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1335. Min Act: -0.0001

Data Index: 262783 (C4 (Web Text))

Max Activating Token Index: 261

Text #13

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1236. Min Act: -0.0002

Data Index: 626137 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1224. Min Act: -0.0001

Data Index: 1274934 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1285. Min Act: -0.0002

Data Index: 309035 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1287. Min Act: -0.0002

Data Index: 379126 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1252. Min Act: -0.0001

Data Index: 863153 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1290. Min Act: -0.0001

Data Index: 1112740 (C4 (Web Text))

Max Activating Token Index: 820

Text #19

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1212. Min Act: -0.0002

Data Index: 847304 (C4 (Web Text))

Max Activating Token Index: 852