Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3991 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6954. Min Range: -1.6954

Max Act: 1.6954. Min Act: -0.0000

Data Index: 288203 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 1.6954. Min Range: -1.6954

Max Act: 1.3082. Min Act: -0.0000

Data Index: 338468 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 1.6954. Min Range: -1.6954

Max Act: 1.3980. Min Act: -0.0000

Data Index: 743755 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 1.6954. Min Range: -1.6954

Max Act: 1.1695. Min Act: -0.0000

Data Index: 932776 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 1.6954. Min Range: -1.6954

Max Act: 1.4505. Min Act: -0.0000

Data Index: 643612 (C4 (Web Text))

Max Activating Token Index: 798

Text #5

Max Range: 1.6954. Min Range: -1.6954

Max Act: 1.1127. Min Act: -0.0000

Data Index: 1264544 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 1.6954. Min Range: -1.6954

Max Act: 1.1740. Min Act: -0.0000

Data Index: 984806 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 1.6954. Min Range: -1.6954

Max Act: 1.1780. Min Act: -0.0000

Data Index: 252942 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 1.6954. Min Range: -1.6954

Max Act: 1.0169. Min Act: -0.0000

Data Index: 596660 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 1.6954. Min Range: -1.6954

Max Act: 1.1398. Min Act: -0.0000

Data Index: 1153723 (C4 (Web Text))

Max Activating Token Index: 766

Text #10

Max Range: 1.6954. Min Range: -1.6954

Max Act: 1.0754. Min Act: -0.0000

Data Index: 460102 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 1.6954. Min Range: -1.6954

Max Act: 1.1071. Min Act: -0.0000

Data Index: 1229284 (C4 (Web Text))

Max Activating Token Index: 557

Text #12

Max Range: 1.6954. Min Range: -1.6954

Max Act: 1.2593. Min Act: -0.0000

Data Index: 205001 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 1.6954. Min Range: -1.6954

Max Act: 1.0683. Min Act: -0.0000

Data Index: 759331 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 1.6954. Min Range: -1.6954

Max Act: 1.1068. Min Act: -0.0000

Data Index: 648245 (C4 (Web Text))

Max Activating Token Index: 1001

Text #15

Max Range: 1.6954. Min Range: -1.6954

Max Act: 1.1204. Min Act: -0.0000

Data Index: 712673 (C4 (Web Text))

Max Activating Token Index: 358

Text #16

Max Range: 1.6954. Min Range: -1.6954

Max Act: 1.0019. Min Act: -0.0000

Data Index: 1086758 (C4 (Web Text))

Max Activating Token Index: 257

Text #17

Max Range: 1.6954. Min Range: -1.6954

Max Act: 1.0285. Min Act: -0.0000

Data Index: 1292929 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 1.6954. Min Range: -1.6954

Max Act: 1.1281. Min Act: -0.0000

Data Index: 641072 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 1.6954. Min Range: -1.6954

Max Act: 1.0187. Min Act: -0.0000

Data Index: 880241 (C4 (Web Text))

Max Activating Token Index: 28