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

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

Neuron 3696 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.7001. Min Act: -0.0000

Data Index: 1493375 (Python Code)

Max Activating Token Index: 751

Text #1

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.6724. Min Act: -0.0000

Data Index: 911188 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.6395. Min Act: -0.0000

Data Index: 1344569 (C4 (Web Text))

Max Activating Token Index: 543

Text #3

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.6200. Min Act: -0.0000

Data Index: 983544 (C4 (Web Text))

Max Activating Token Index: 450

Text #4

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.6229. Min Act: 0.0001

Data Index: 163361 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.6064. Min Act: -0.0000

Data Index: 1114666 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.6270. Min Act: -0.0000

Data Index: 1285971 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.6012. Min Act: -0.0000

Data Index: 359481 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.6054. Min Act: -0.0000

Data Index: 120393 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.5849. Min Act: -0.0000

Data Index: 1375842 (Python Code)

Max Activating Token Index: 431

Text #10

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.5765. Min Act: -0.0000

Data Index: 1524113 (Python Code)

Max Activating Token Index: 129

Text #11

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.5765. Min Act: -0.0000

Data Index: 1469788 (Python Code)

Max Activating Token Index: 891

Text #12

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.5709. Min Act: -0.0000

Data Index: 1557006 (Python Code)

Max Activating Token Index: 402

Text #13

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.5695. Min Act: -0.0000

Data Index: 1255439 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.5456. Min Act: 0.0000

Data Index: 1073438 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.5749. Min Act: -0.0000

Data Index: 1502462 (Python Code)

Max Activating Token Index: 360

Text #16

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.5460. Min Act: -0.0000

Data Index: 782208 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.5150. Min Act: -0.0000

Data Index: 114206 (C4 (Web Text))

Max Activating Token Index: 438

Text #18

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.5255. Min Act: -0.0000

Data Index: 865403 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 0.7001. Min Range: -0.7001

Max Act: 0.5394. Min Act: -0.0000

Data Index: 1321516 (C4 (Web Text))

Max Activating Token Index: 816