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

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

Neuron 1577 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6857. Min Range: -1.6857

Max Act: 1.6857. Min Act: -0.0000

Data Index: 218612 (C4 (Web Text))

Max Activating Token Index: 501

Text #1

Max Range: 1.6857. Min Range: -1.6857

Max Act: 1.6530. Min Act: -0.0000

Data Index: 75593 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 1.6857. Min Range: -1.6857

Max Act: 1.5128. Min Act: 0.0000

Data Index: 1138860 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 1.6857. Min Range: -1.6857

Max Act: 1.4717. Min Act: -0.0000

Data Index: 796284 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 1.6857. Min Range: -1.6857

Max Act: 1.4470. Min Act: -0.0000

Data Index: 400710 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 1.6857. Min Range: -1.6857

Max Act: 1.4415. Min Act: 0.0000

Data Index: 1333189 (C4 (Web Text))

Max Activating Token Index: 484

Text #6

Max Range: 1.6857. Min Range: -1.6857

Max Act: 1.4906. Min Act: -0.0000

Data Index: 584586 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 1.6857. Min Range: -1.6857

Max Act: 1.3937. Min Act: -0.0000

Data Index: 57134 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 1.6857. Min Range: -1.6857

Max Act: 1.4606. Min Act: -0.0000

Data Index: 997343 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 1.6857. Min Range: -1.6857

Max Act: 1.4666. Min Act: -0.0000

Data Index: 73507 (C4 (Web Text))

Max Activating Token Index: 1022

Text #10

Max Range: 1.6857. Min Range: -1.6857

Max Act: 1.4291. Min Act: -0.0000

Data Index: 939286 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 1.6857. Min Range: -1.6857

Max Act: 1.3526. Min Act: -0.0000

Data Index: 475628 (C4 (Web Text))

Max Activating Token Index: 738

Text #12

Max Range: 1.6857. Min Range: -1.6857

Max Act: 1.5160. Min Act: -0.0000

Data Index: 840215 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 1.6857. Min Range: -1.6857

Max Act: 1.4021. Min Act: -0.0000

Data Index: 1238778 (C4 (Web Text))

Max Activating Token Index: 814

Text #14

Max Range: 1.6857. Min Range: -1.6857

Max Act: 1.3982. Min Act: -0.0000

Data Index: 226939 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 1.6857. Min Range: -1.6857

Max Act: 1.3104. Min Act: -0.0000

Data Index: 1082259 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 1.6857. Min Range: -1.6857

Max Act: 1.3695. Min Act: -0.0000

Data Index: 239590 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 1.6857. Min Range: -1.6857

Max Act: 1.3513. Min Act: -0.0000

Data Index: 582301 (C4 (Web Text))

Max Activating Token Index: 993

Text #18

Max Range: 1.6857. Min Range: -1.6857

Max Act: 1.3348. Min Act: -0.0000

Data Index: 978997 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 1.6857. Min Range: -1.6857

Max Act: 1.2719. Min Act: -0.0000

Data Index: 292462 (C4 (Web Text))

Max Activating Token Index: 930