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

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

Neuron 52 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4491. Min Range: -0.4491

Max Act: 0.4491. Min Act: -0.0001

Data Index: 1352542 (C4 (Web Text))

Max Activating Token Index: 650

Text #1

Max Range: 0.4491. Min Range: -0.4491

Max Act: 0.3483. Min Act: -0.0001

Data Index: 55538 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 0.4491. Min Range: -0.4491

Max Act: 0.2804. Min Act: -0.0001

Data Index: 1134380 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 0.4491. Min Range: -0.4491

Max Act: 0.2914. Min Act: -0.0001

Data Index: 1024450 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 0.4491. Min Range: -0.4491

Max Act: 0.2698. Min Act: -0.0001

Data Index: 239993 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 0.4491. Min Range: -0.4491

Max Act: 0.2759. Min Act: -0.0001

Data Index: 352705 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 0.4491. Min Range: -0.4491

Max Act: 0.2630. Min Act: -0.0001

Data Index: 605705 (C4 (Web Text))

Max Activating Token Index: 735

Text #7

Max Range: 0.4491. Min Range: -0.4491

Max Act: 0.2409. Min Act: -0.0000

Data Index: 313184 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 0.4491. Min Range: -0.4491

Max Act: 0.2398. Min Act: -0.0001

Data Index: 554755 (C4 (Web Text))

Max Activating Token Index: 643

Text #9

Max Range: 0.4491. Min Range: -0.4491

Max Act: 0.2389. Min Act: -0.0001

Data Index: 1297745 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 0.4491. Min Range: -0.4491

Max Act: 0.2222. Min Act: -0.0001

Data Index: 253010 (C4 (Web Text))

Max Activating Token Index: 288

Text #11

Max Range: 0.4491. Min Range: -0.4491

Max Act: 0.2375. Min Act: -0.0001

Data Index: 1121766 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 0.4491. Min Range: -0.4491

Max Act: 0.2127. Min Act: -0.0001

Data Index: 397913 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 0.4491. Min Range: -0.4491

Max Act: 0.2357. Min Act: -0.0001

Data Index: 1092563 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 0.4491. Min Range: -0.4491

Max Act: 0.2326. Min Act: -0.0001

Data Index: 966494 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 0.4491. Min Range: -0.4491

Max Act: 0.2137. Min Act: -0.0001

Data Index: 1296064 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 0.4491. Min Range: -0.4491

Max Act: 0.2295. Min Act: -0.0000

Data Index: 761453 (C4 (Web Text))

Max Activating Token Index: 901

Text #17

Max Range: 0.4491. Min Range: -0.4491

Max Act: 0.2200. Min Act: -0.0001

Data Index: 651350 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 0.4491. Min Range: -0.4491

Max Act: 0.2287. Min Act: -0.0001

Data Index: 377904 (C4 (Web Text))

Max Activating Token Index: 799

Text #19

Max Range: 0.4491. Min Range: -0.4491

Max Act: 0.2130. Min Act: -0.0001

Data Index: 165463 (C4 (Web Text))

Max Activating Token Index: 1000