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

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

Neuron 1942 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1782. Min Act: -0.0005

Data Index: 218966 (C4 (Web Text))

Max Activating Token Index: 875

Text #1

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1559. Min Act: -0.0005

Data Index: 571281 (C4 (Web Text))

Max Activating Token Index: 397

Text #2

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1433. Min Act: -0.0005

Data Index: 223973 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1372. Min Act: -0.0005

Data Index: 1306484 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1540. Min Act: -0.0005

Data Index: 21107 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1407. Min Act: -0.0005

Data Index: 436348 (C4 (Web Text))

Max Activating Token Index: 907

Text #6

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1353. Min Act: -0.0005

Data Index: 1117307 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1216. Min Act: -0.0005

Data Index: 44425 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1342. Min Act: -0.0005

Data Index: 203074 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1294. Min Act: -0.0005

Data Index: 238784 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1266. Min Act: -0.0005

Data Index: 1251884 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1203. Min Act: -0.0005

Data Index: 202611 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1274. Min Act: -0.0005

Data Index: 1177529 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1284. Min Act: -0.0005

Data Index: 884902 (C4 (Web Text))

Max Activating Token Index: 701

Text #14

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1233. Min Act: -0.0005

Data Index: 74568 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1133. Min Act: -0.0005

Data Index: 628540 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1273. Min Act: -0.0005

Data Index: 1103676 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1365. Min Act: -0.0005

Data Index: 136817 (C4 (Web Text))

Max Activating Token Index: 522

Text #18

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1220. Min Act: -0.0005

Data Index: 1194139 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1222. Min Act: -0.0005

Data Index: 207370 (C4 (Web Text))

Max Activating Token Index: 986