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

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

Neuron 3538 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1741. Min Act: -0.0002

Data Index: 918488 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1385. Min Act: -0.0002

Data Index: 257849 (C4 (Web Text))

Max Activating Token Index: 401

Text #2

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1406. Min Act: -0.0002

Data Index: 206433 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1440. Min Act: -0.0002

Data Index: 452496 (C4 (Web Text))

Max Activating Token Index: 508

Text #4

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1358. Min Act: -0.0002

Data Index: 934382 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1290. Min Act: -0.0002

Data Index: 502863 (C4 (Web Text))

Max Activating Token Index: 504

Text #6

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1276. Min Act: -0.0002

Data Index: 852472 (C4 (Web Text))

Max Activating Token Index: 656

Text #7

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1267. Min Act: -0.0002

Data Index: 654446 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1206. Min Act: -0.0002

Data Index: 395978 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1275. Min Act: -0.0002

Data Index: 884688 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1117. Min Act: -0.0002

Data Index: 612514 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1040. Min Act: -0.0002

Data Index: 1218338 (C4 (Web Text))

Max Activating Token Index: 429

Text #12

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1106. Min Act: -0.0002

Data Index: 844581 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1117. Min Act: -0.0002

Data Index: 636919 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1106. Min Act: -0.0002

Data Index: 522874 (C4 (Web Text))

Max Activating Token Index: 525

Text #15

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1020. Min Act: -0.0002

Data Index: 1092951 (C4 (Web Text))

Max Activating Token Index: 618

Text #16

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1111. Min Act: -0.0002

Data Index: 600273 (C4 (Web Text))

Max Activating Token Index: 476

Text #17

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1062. Min Act: -0.0002

Data Index: 1163817 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1073. Min Act: -0.0002

Data Index: 547742 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 0.1741. Min Range: -0.1741

Max Act: 0.1033. Min Act: -0.0002

Data Index: 196307 (C4 (Web Text))

Max Activating Token Index: 408