Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3472 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.2342. Min Act: -0.0000

Data Index: 1298243 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.2340. Min Act: -0.0000

Data Index: 460917 (C4 (Web Text))

Max Activating Token Index: 672

Text #2

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1532. Min Act: -0.0000

Data Index: 833566 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1893. Min Act: -0.0000

Data Index: 1127124 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1797. Min Act: -0.0000

Data Index: 1093633 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1528. Min Act: -0.0000

Data Index: 1120589 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1707. Min Act: -0.0000

Data Index: 776533 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1532. Min Act: -0.0000

Data Index: 1270819 (C4 (Web Text))

Max Activating Token Index: 123

Text #8

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1544. Min Act: -0.0000

Data Index: 607482 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1504. Min Act: -0.0000

Data Index: 1174882 (C4 (Web Text))

Max Activating Token Index: 334

Text #10

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1468. Min Act: -0.0000

Data Index: 996891 (C4 (Web Text))

Max Activating Token Index: 693

Text #11

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1229. Min Act: -0.0000

Data Index: 370114 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1319. Min Act: -0.0000

Data Index: 1070911 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1253. Min Act: -0.0000

Data Index: 713678 (C4 (Web Text))

Max Activating Token Index: 1007

Text #14

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1338. Min Act: -0.0000

Data Index: 377184 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1294. Min Act: -0.0000

Data Index: 1155691 (C4 (Web Text))

Max Activating Token Index: 594

Text #16

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1316. Min Act: 0.0000

Data Index: 516842 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1248. Min Act: -0.0000

Data Index: 379522 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1214. Min Act: 0.0000

Data Index: 81988 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 0.2342. Min Range: -0.2342

Max Act: 0.1194. Min Act: -0.0000

Data Index: 370050 (C4 (Web Text))

Max Activating Token Index: 620