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

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

Neuron 942 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.2447. Min Act: -0.0002

Data Index: 1169566 (C4 (Web Text))

Max Activating Token Index: 999

Text #1

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.2221. Min Act: -0.0001

Data Index: 489322 (C4 (Web Text))

Max Activating Token Index: 1009

Text #2

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.2261. Min Act: -0.0002

Data Index: 253927 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.2114. Min Act: -0.0001

Data Index: 439613 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.2258. Min Act: -0.0002

Data Index: 765606 (C4 (Web Text))

Max Activating Token Index: 928

Text #5

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.2028. Min Act: -0.0002

Data Index: 959500 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.2244. Min Act: -0.0001

Data Index: 114576 (C4 (Web Text))

Max Activating Token Index: 777

Text #7

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.2146. Min Act: -0.0002

Data Index: 70404 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.2235. Min Act: -0.0001

Data Index: 919877 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.2062. Min Act: -0.0002

Data Index: 1090605 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.2177. Min Act: -0.0001

Data Index: 1175172 (C4 (Web Text))

Max Activating Token Index: 986

Text #11

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.2058. Min Act: -0.0002

Data Index: 870213 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.2052. Min Act: -0.0001

Data Index: 25951 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.2057. Min Act: -0.0002

Data Index: 1220039 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1929. Min Act: -0.0002

Data Index: 357961 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.2011. Min Act: -0.0001

Data Index: 483652 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.2068. Min Act: -0.0002

Data Index: 100553 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1919. Min Act: -0.0001

Data Index: 503574 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1954. Min Act: -0.0002

Data Index: 462091 (C4 (Web Text))

Max Activating Token Index: 936

Text #19

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.2046. Min Act: -0.0001

Data Index: 1104069 (C4 (Web Text))

Max Activating Token Index: 826