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

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

Neuron 2956 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2644. Min Act: -0.0001

Data Index: 1288962 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2362. Min Act: -0.0001

Data Index: 1107987 (C4 (Web Text))

Max Activating Token Index: 323

Text #2

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2350. Min Act: -0.0001

Data Index: 312131 (C4 (Web Text))

Max Activating Token Index: 134

Text #3

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2201. Min Act: -0.0001

Data Index: 317658 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2117. Min Act: -0.0001

Data Index: 1210344 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2186. Min Act: -0.0001

Data Index: 170891 (C4 (Web Text))

Max Activating Token Index: 301

Text #6

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2120. Min Act: -0.0001

Data Index: 400662 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2242. Min Act: -0.0001

Data Index: 19431 (C4 (Web Text))

Max Activating Token Index: 974

Text #8

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.1987. Min Act: -0.0001

Data Index: 3284 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.1974. Min Act: -0.0001

Data Index: 1113676 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2187. Min Act: -0.0000

Data Index: 1176884 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2118. Min Act: -0.0001

Data Index: 554490 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2023. Min Act: -0.0001

Data Index: 236978 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.1951. Min Act: -0.0001

Data Index: 1293064 (C4 (Web Text))

Max Activating Token Index: 622

Text #14

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2006. Min Act: -0.0000

Data Index: 539139 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2038. Min Act: -0.0001

Data Index: 92514 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.1999. Min Act: -0.0001

Data Index: 934520 (C4 (Web Text))

Max Activating Token Index: 1018

Text #17

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.1961. Min Act: -0.0001

Data Index: 148106 (C4 (Web Text))

Max Activating Token Index: 535

Text #18

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.1963. Min Act: -0.0001

Data Index: 748294 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.1897. Min Act: -0.0001

Data Index: 509353 (C4 (Web Text))

Max Activating Token Index: 883