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

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

Neuron 19 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9996. Min Range: -2.9996

Max Act: 2.9996. Min Act: -0.0000

Data Index: 146364 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 2.9996. Min Range: -2.9996

Max Act: 2.8872. Min Act: -0.0000

Data Index: 1010774 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 2.9996. Min Range: -2.9996

Max Act: 2.7570. Min Act: -0.0000

Data Index: 149322 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 2.9996. Min Range: -2.9996

Max Act: 2.6113. Min Act: -0.0000

Data Index: 6556 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 2.9996. Min Range: -2.9996

Max Act: 2.4139. Min Act: -0.0000

Data Index: 242015 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 2.9996. Min Range: -2.9996

Max Act: 2.3206. Min Act: -0.0000

Data Index: 917010 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 2.9996. Min Range: -2.9996

Max Act: 2.4281. Min Act: -0.0000

Data Index: 856615 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 2.9996. Min Range: -2.9996

Max Act: 2.3743. Min Act: -0.0000

Data Index: 1164422 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 2.9996. Min Range: -2.9996

Max Act: 2.4489. Min Act: -0.0000

Data Index: 1213343 (C4 (Web Text))

Max Activating Token Index: 1019

Text #9

Max Range: 2.9996. Min Range: -2.9996

Max Act: 2.2582. Min Act: -0.0000

Data Index: 458027 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 2.9996. Min Range: -2.9996

Max Act: 2.2126. Min Act: -0.0000

Data Index: 871716 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 2.9996. Min Range: -2.9996

Max Act: 2.1947. Min Act: -0.0000

Data Index: 348515 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 2.9996. Min Range: -2.9996

Max Act: 2.0363. Min Act: -0.0000

Data Index: 1324314 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 2.9996. Min Range: -2.9996

Max Act: 2.1380. Min Act: -0.0000

Data Index: 152219 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 2.9996. Min Range: -2.9996

Max Act: 2.1002. Min Act: -0.0000

Data Index: 859217 (C4 (Web Text))

Max Activating Token Index: 666

Text #15

Max Range: 2.9996. Min Range: -2.9996

Max Act: 2.0720. Min Act: -0.0000

Data Index: 1058159 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 2.9996. Min Range: -2.9996

Max Act: 2.0599. Min Act: -0.0000

Data Index: 139869 (C4 (Web Text))

Max Activating Token Index: 781

Text #17

Max Range: 2.9996. Min Range: -2.9996

Max Act: 2.0629. Min Act: -0.0000

Data Index: 1070218 (C4 (Web Text))

Max Activating Token Index: 959

Text #18

Max Range: 2.9996. Min Range: -2.9996

Max Act: 1.9232. Min Act: -0.0000

Data Index: 301121 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 2.9996. Min Range: -2.9996

Max Act: 1.9114. Min Act: -0.0000

Data Index: 79860 (C4 (Web Text))

Max Activating Token Index: 856