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

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

Neuron 1443 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: 0.7516. Min Range: -0.7516

Max Act: 0.7516. Min Act: -0.0000

Data Index: 1641818 (Python Code)

Max Activating Token Index: 607

Text #1

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.7225. Min Act: -0.0000

Data Index: 1368822 (Python Code)

Max Activating Token Index: 913

Text #2

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.7309. Min Act: -0.0000

Data Index: 1366365 (Python Code)

Max Activating Token Index: 335

Text #3

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.7260. Min Act: -0.0000

Data Index: 1371280 (Python Code)

Max Activating Token Index: 889

Text #4

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.6741. Min Act: -0.0000

Data Index: 1584231 (Python Code)

Max Activating Token Index: 524

Text #5

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.7068. Min Act: -0.0000

Data Index: 1516436 (Python Code)

Max Activating Token Index: 448

Text #6

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.6092. Min Act: -0.0000

Data Index: 1601414 (Python Code)

Max Activating Token Index: 748

Text #7

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.6221. Min Act: -0.0000

Data Index: 1486452 (Python Code)

Max Activating Token Index: 851

Text #8

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.6800. Min Act: -0.0000

Data Index: 1417895 (Python Code)

Max Activating Token Index: 999

Text #9

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.6293. Min Act: -0.0000

Data Index: 1608345 (Python Code)

Max Activating Token Index: 383

Text #10

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.6182. Min Act: -0.0000

Data Index: 1507141 (Python Code)

Max Activating Token Index: 64

Text #11

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.5542. Min Act: -0.0000

Data Index: 1140448 (C4 (Web Text))

Max Activating Token Index: 438

Text #12

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.5040. Min Act: -0.0000

Data Index: 225680 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.5067. Min Act: -0.0000

Data Index: 863317 (C4 (Web Text))

Max Activating Token Index: 244

Text #14

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.4978. Min Act: -0.0000

Data Index: 1544324 (Python Code)

Max Activating Token Index: 82

Text #15

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.4792. Min Act: -0.0000

Data Index: 1508780 (Python Code)

Max Activating Token Index: 1010

Text #16

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.4436. Min Act: -0.0000

Data Index: 1552275 (Python Code)

Max Activating Token Index: 760

Text #17

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.4230. Min Act: -0.0000

Data Index: 642886 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.4257. Min Act: -0.0000

Data Index: 1162777 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 0.7516. Min Range: -0.7516

Max Act: 0.3967. Min Act: -0.0000

Data Index: 1410803 (Python Code)

Max Activating Token Index: 12