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

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

Neuron 4480 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.4243. Min Act: -0.0000

Data Index: 1068056 (C4 (Web Text))

Max Activating Token Index: 607

Text #1

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3665. Min Act: -0.0000

Data Index: 396527 (C4 (Web Text))

Max Activating Token Index: 798

Text #2

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3325. Min Act: -0.0000

Data Index: 191250 (C4 (Web Text))

Max Activating Token Index: 998

Text #3

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3059. Min Act: -0.0000

Data Index: 838272 (C4 (Web Text))

Max Activating Token Index: 605

Text #4

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.3013. Min Act: -0.0000

Data Index: 1242940 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.2596. Min Act: -0.0000

Data Index: 195296 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.2699. Min Act: -0.0000

Data Index: 207251 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.2792. Min Act: -0.0000

Data Index: 26645 (C4 (Web Text))

Max Activating Token Index: 303

Text #8

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.2732. Min Act: -0.0000

Data Index: 901922 (C4 (Web Text))

Max Activating Token Index: 926

Text #9

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.2150. Min Act: -0.0000

Data Index: 675276 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.2109. Min Act: -0.0000

Data Index: 1646704 (Python Code)

Max Activating Token Index: 745

Text #11

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.2156. Min Act: -0.0000

Data Index: 1143083 (C4 (Web Text))

Max Activating Token Index: 582

Text #12

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.2187. Min Act: -0.0000

Data Index: 1151770 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.2002. Min Act: -0.0000

Data Index: 96392 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.2130. Min Act: -0.0000

Data Index: 801649 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.1984. Min Act: -0.0000

Data Index: 611724 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.2054. Min Act: -0.0000

Data Index: 1253629 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.1852. Min Act: -0.0000

Data Index: 1564669 (Python Code)

Max Activating Token Index: 316

Text #18

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.1937. Min Act: -0.0000

Data Index: 799776 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 0.4243. Min Range: -0.4243

Max Act: 0.1842. Min Act: -0.0000

Data Index: 1548470 (Python Code)

Max Activating Token Index: 234