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

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

Neuron 5855 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: 3.1337. Min Range: -3.1337

Max Act: 3.1337. Min Act: -0.0000

Data Index: 125014 (C4 (Web Text))

Max Activating Token Index: 800

Text #1

Max Range: 3.1337. Min Range: -3.1337

Max Act: 2.3204. Min Act: -0.0000

Data Index: 1418549 (Python Code)

Max Activating Token Index: 972

Text #2

Max Range: 3.1337. Min Range: -3.1337

Max Act: 1.8758. Min Act: -0.0000

Data Index: 253500 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 3.1337. Min Range: -3.1337

Max Act: 1.8163. Min Act: -0.0000

Data Index: 1383046 (Python Code)

Max Activating Token Index: 677

Text #4

Max Range: 3.1337. Min Range: -3.1337

Max Act: 1.7100. Min Act: -0.0000

Data Index: 1534767 (Python Code)

Max Activating Token Index: 708

Text #5

Max Range: 3.1337. Min Range: -3.1337

Max Act: 1.7745. Min Act: -0.0000

Data Index: 1293521 (C4 (Web Text))

Max Activating Token Index: 830

Text #6

Max Range: 3.1337. Min Range: -3.1337

Max Act: 1.7035. Min Act: -0.0000

Data Index: 1458931 (Python Code)

Max Activating Token Index: 668

Text #7

Max Range: 3.1337. Min Range: -3.1337

Max Act: 1.5005. Min Act: -0.0000

Data Index: 1374961 (Python Code)

Max Activating Token Index: 149

Text #8

Max Range: 3.1337. Min Range: -3.1337

Max Act: 1.5738. Min Act: -0.0000

Data Index: 1468436 (Python Code)

Max Activating Token Index: 991

Text #9

Max Range: 3.1337. Min Range: -3.1337

Max Act: 1.6334. Min Act: -0.0000

Data Index: 1525828 (Python Code)

Max Activating Token Index: 701

Text #10

Max Range: 3.1337. Min Range: -3.1337

Max Act: 1.4339. Min Act: 0.0001

Data Index: 1275410 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 3.1337. Min Range: -3.1337

Max Act: 1.3303. Min Act: -0.0000

Data Index: 1406353 (Python Code)

Max Activating Token Index: 245

Text #12

Max Range: 3.1337. Min Range: -3.1337

Max Act: 1.1979. Min Act: -0.0000

Data Index: 1552418 (Python Code)

Max Activating Token Index: 267

Text #13

Max Range: 3.1337. Min Range: -3.1337

Max Act: 1.1627. Min Act: -0.0000

Data Index: 1580398 (Python Code)

Max Activating Token Index: 796

Text #14

Max Range: 3.1337. Min Range: -3.1337

Max Act: 1.0956. Min Act: -0.0000

Data Index: 1291544 (C4 (Web Text))

Max Activating Token Index: 630

Text #15

Max Range: 3.1337. Min Range: -3.1337

Max Act: 1.2070. Min Act: -0.0000

Data Index: 1046525 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 3.1337. Min Range: -3.1337

Max Act: 0.8258. Min Act: -0.0000

Data Index: 284484 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 3.1337. Min Range: -3.1337

Max Act: 1.1212. Min Act: 0.0001

Data Index: 528014 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 3.1337. Min Range: -3.1337

Max Act: 1.0756. Min Act: -0.0000

Data Index: 1515081 (Python Code)

Max Activating Token Index: 19

Text #19

Max Range: 3.1337. Min Range: -3.1337

Max Act: 1.0220. Min Act: -0.0000

Data Index: 1365152 (Python Code)

Max Activating Token Index: 353