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

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

Neuron 4739 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.5293. Min Act: -0.0000

Data Index: 1454602 (Python Code)

Max Activating Token Index: 27

Text #1

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.5293. Min Act: -0.0000

Data Index: 1494834 (Python Code)

Max Activating Token Index: 27

Text #2

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.3792. Min Act: -0.0000

Data Index: 1537157 (Python Code)

Max Activating Token Index: 29

Text #3

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.6186. Min Act: -0.0000

Data Index: 1377602 (Python Code)

Max Activating Token Index: 219

Text #4

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.7389. Min Act: -0.0000

Data Index: 1526626 (Python Code)

Max Activating Token Index: 403

Text #5

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.5248. Min Act: -0.0000

Data Index: 1421855 (Python Code)

Max Activating Token Index: 339

Text #6

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.2597. Min Act: -0.0000

Data Index: 1382493 (Python Code)

Max Activating Token Index: 167

Text #7

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.3004. Min Act: -0.0000

Data Index: 1555680 (Python Code)

Max Activating Token Index: 218

Text #8

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.2750. Min Act: -0.0000

Data Index: 1579056 (Python Code)

Max Activating Token Index: 18

Text #9

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.1710. Min Act: -0.0000

Data Index: 1621619 (Python Code)

Max Activating Token Index: 227

Text #10

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.2274. Min Act: -0.0000

Data Index: 1392871 (Python Code)

Max Activating Token Index: 41

Text #11

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.2807. Min Act: -0.0000

Data Index: 1552362 (Python Code)

Max Activating Token Index: 904

Text #12

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.2444. Min Act: -0.0000

Data Index: 1586441 (Python Code)

Max Activating Token Index: 39

Text #13

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.0749. Min Act: -0.0000

Data Index: 1444374 (Python Code)

Max Activating Token Index: 36

Text #14

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.4364. Min Act: -0.0000

Data Index: 1484973 (Python Code)

Max Activating Token Index: 198

Text #15

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.1057. Min Act: -0.0000

Data Index: 1423235 (Python Code)

Max Activating Token Index: 112

Text #16

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.1181. Min Act: -0.0000

Data Index: 1626013 (Python Code)

Max Activating Token Index: 41

Text #17

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.0959. Min Act: -0.0000

Data Index: 1519932 (Python Code)

Max Activating Token Index: 40

Text #18

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.0241. Min Act: -0.0000

Data Index: 1361228 (Python Code)

Max Activating Token Index: 800

Text #19

Max Range: 1.7389. Min Range: -1.7389

Max Act: 1.0854. Min Act: -0.0000

Data Index: 1540608 (Python Code)

Max Activating Token Index: 110