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

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

Neuron 127 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5707. Min Range: -0.5707

Max Act: 0.5695. Min Act: -0.0001

Data Index: 1126051 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 0.5707. Min Range: -0.5707

Max Act: 0.5707. Min Act: -0.0001

Data Index: 1046065 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 0.5707. Min Range: -0.5707

Max Act: 0.5306. Min Act: -0.0001

Data Index: 1293603 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 0.5707. Min Range: -0.5707

Max Act: 0.5498. Min Act: -0.0001

Data Index: 338139 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 0.5707. Min Range: -0.5707

Max Act: 0.5154. Min Act: -0.0001

Data Index: 537985 (C4 (Web Text))

Max Activating Token Index: 973

Text #5

Max Range: 0.5707. Min Range: -0.5707

Max Act: 0.5019. Min Act: -0.0001

Data Index: 1079195 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 0.5707. Min Range: -0.5707

Max Act: 0.5107. Min Act: -0.0001

Data Index: 730959 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.5707. Min Range: -0.5707

Max Act: 0.5073. Min Act: -0.0001

Data Index: 797138 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 0.5707. Min Range: -0.5707

Max Act: 0.5270. Min Act: -0.0001

Data Index: 298564 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 0.5707. Min Range: -0.5707

Max Act: 0.5049. Min Act: -0.0001

Data Index: 1334721 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 0.5707. Min Range: -0.5707

Max Act: 0.5189. Min Act: -0.0001

Data Index: 261731 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 0.5707. Min Range: -0.5707

Max Act: 0.5106. Min Act: -0.0001

Data Index: 122291 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 0.5707. Min Range: -0.5707

Max Act: 0.5179. Min Act: -0.0001

Data Index: 379776 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 0.5707. Min Range: -0.5707

Max Act: 0.4982. Min Act: -0.0001

Data Index: 748002 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 0.5707. Min Range: -0.5707

Max Act: 0.4975. Min Act: -0.0001

Data Index: 1051489 (C4 (Web Text))

Max Activating Token Index: 1018

Text #15

Max Range: 0.5707. Min Range: -0.5707

Max Act: 0.4816. Min Act: -0.0001

Data Index: 294017 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 0.5707. Min Range: -0.5707

Max Act: 0.5145. Min Act: -0.0001

Data Index: 954459 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 0.5707. Min Range: -0.5707

Max Act: 0.4619. Min Act: -0.0001

Data Index: 1329009 (C4 (Web Text))

Max Activating Token Index: 252

Text #18

Max Range: 0.5707. Min Range: -0.5707

Max Act: 0.4928. Min Act: -0.0001

Data Index: 1268095 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.5707. Min Range: -0.5707

Max Act: 0.4691. Min Act: -0.0001

Data Index: 524540 (C4 (Web Text))

Max Activating Token Index: 129