Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3937 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2928. Min Act: -0.0001

Data Index: 715161 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2616. Min Act: -0.0001

Data Index: 271169 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2494. Min Act: -0.0001

Data Index: 587623 (C4 (Web Text))

Max Activating Token Index: 661

Text #3

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2150. Min Act: -0.0000

Data Index: 1097192 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2211. Min Act: -0.0001

Data Index: 16058 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2109. Min Act: -0.0000

Data Index: 646540 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2042. Min Act: -0.0001

Data Index: 546249 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2236. Min Act: -0.0001

Data Index: 1199719 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.1926. Min Act: -0.0000

Data Index: 601890 (C4 (Web Text))

Max Activating Token Index: 838

Text #9

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2142. Min Act: -0.0000

Data Index: 1222291 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.1818. Min Act: -0.0000

Data Index: 428033 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2002. Min Act: -0.0000

Data Index: 1345556 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.1817. Min Act: -0.0000

Data Index: 91381 (C4 (Web Text))

Max Activating Token Index: 453

Text #13

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.1940. Min Act: -0.0001

Data Index: 1144474 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.1861. Min Act: -0.0000

Data Index: 721481 (C4 (Web Text))

Max Activating Token Index: 866

Text #15

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.1936. Min Act: -0.0001

Data Index: 766257 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2139. Min Act: -0.0001

Data Index: 249531 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.1907. Min Act: -0.0000

Data Index: 1136285 (C4 (Web Text))

Max Activating Token Index: 530

Text #18

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.1966. Min Act: -0.0000

Data Index: 512463 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.1866. Min Act: -0.0000

Data Index: 346400 (C4 (Web Text))

Max Activating Token Index: 739