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

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

Neuron 1380 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: 1.1430. Min Range: -1.1430

Max Act: 1.1430. Min Act: -0.0000

Data Index: 1035221 (C4 (Web Text))

Max Activating Token Index: 602

Text #1

Max Range: 1.1430. Min Range: -1.1430

Max Act: 1.1112. Min Act: -0.0000

Data Index: 1654090 (Python Code)

Max Activating Token Index: 105

Text #2

Max Range: 1.1430. Min Range: -1.1430

Max Act: 0.9400. Min Act: -0.0000

Data Index: 1590809 (Python Code)

Max Activating Token Index: 699

Text #3

Max Range: 1.1430. Min Range: -1.1430

Max Act: 0.9908. Min Act: -0.0000

Data Index: 1605384 (Python Code)

Max Activating Token Index: 921

Text #4

Max Range: 1.1430. Min Range: -1.1430

Max Act: 0.9459. Min Act: -0.0000

Data Index: 1571152 (Python Code)

Max Activating Token Index: 877

Text #5

Max Range: 1.1430. Min Range: -1.1430

Max Act: 0.9274. Min Act: -0.0000

Data Index: 1582565 (Python Code)

Max Activating Token Index: 263

Text #6

Max Range: 1.1430. Min Range: -1.1430

Max Act: 0.8642. Min Act: -0.0000

Data Index: 604549 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 1.1430. Min Range: -1.1430

Max Act: 0.9698. Min Act: -0.0000

Data Index: 1360720 (Python Code)

Max Activating Token Index: 313

Text #8

Max Range: 1.1430. Min Range: -1.1430

Max Act: 1.0029. Min Act: -0.0000

Data Index: 313918 (C4 (Web Text))

Max Activating Token Index: 234

Text #9

Max Range: 1.1430. Min Range: -1.1430

Max Act: 0.9586. Min Act: -0.0000

Data Index: 1625571 (Python Code)

Max Activating Token Index: 960

Text #10

Max Range: 1.1430. Min Range: -1.1430

Max Act: 0.9003. Min Act: -0.0000

Data Index: 592829 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 1.1430. Min Range: -1.1430

Max Act: 0.9322. Min Act: -0.0000

Data Index: 1618743 (Python Code)

Max Activating Token Index: 322

Text #12

Max Range: 1.1430. Min Range: -1.1430

Max Act: 0.8376. Min Act: -0.0000

Data Index: 1644530 (Python Code)

Max Activating Token Index: 496

Text #13

Max Range: 1.1430. Min Range: -1.1430

Max Act: 0.8381. Min Act: -0.0000

Data Index: 1418539 (Python Code)

Max Activating Token Index: 167

Text #14

Max Range: 1.1430. Min Range: -1.1430

Max Act: 0.8392. Min Act: -0.0000

Data Index: 1472109 (Python Code)

Max Activating Token Index: 60

Text #15

Max Range: 1.1430. Min Range: -1.1430

Max Act: 0.8270. Min Act: -0.0000

Data Index: 1524280 (Python Code)

Max Activating Token Index: 315

Text #16

Max Range: 1.1430. Min Range: -1.1430

Max Act: 0.8383. Min Act: -0.0000

Data Index: 1457070 (Python Code)

Max Activating Token Index: 868

Text #17

Max Range: 1.1430. Min Range: -1.1430

Max Act: 0.7897. Min Act: -0.0000

Data Index: 1602049 (Python Code)

Max Activating Token Index: 536

Text #18

Max Range: 1.1430. Min Range: -1.1430

Max Act: 0.8278. Min Act: -0.0000

Data Index: 1563708 (Python Code)

Max Activating Token Index: 306

Text #19

Max Range: 1.1430. Min Range: -1.1430

Max Act: 0.7526. Min Act: -0.0000

Data Index: 1597959 (Python Code)

Max Activating Token Index: 797