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

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

Neuron 854 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1294. Min Act: -0.0000

Data Index: 609194 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1341. Min Act: -0.0000

Data Index: 1067190 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1201. Min Act: -0.0000

Data Index: 710390 (C4 (Web Text))

Max Activating Token Index: 294

Text #3

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1154. Min Act: -0.0000

Data Index: 864595 (C4 (Web Text))

Max Activating Token Index: 910

Text #4

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1144. Min Act: -0.0000

Data Index: 660278 (C4 (Web Text))

Max Activating Token Index: 439

Text #5

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1224. Min Act: -0.0000

Data Index: 501932 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1049. Min Act: -0.0000

Data Index: 1253954 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1124. Min Act: -0.0000

Data Index: 196184 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1081. Min Act: -0.0001

Data Index: 1210984 (C4 (Web Text))

Max Activating Token Index: 568

Text #9

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1115. Min Act: -0.0000

Data Index: 360226 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1116. Min Act: -0.0001

Data Index: 400082 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1144. Min Act: -0.0000

Data Index: 71990 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1102. Min Act: -0.0000

Data Index: 556051 (C4 (Web Text))

Max Activating Token Index: 1014

Text #13

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1141. Min Act: -0.0001

Data Index: 371848 (C4 (Web Text))

Max Activating Token Index: 1002

Text #14

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1050. Min Act: -0.0000

Data Index: 240160 (C4 (Web Text))

Max Activating Token Index: 604

Text #15

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1125. Min Act: -0.0000

Data Index: 1073228 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1049. Min Act: -0.0000

Data Index: 715326 (C4 (Web Text))

Max Activating Token Index: 915

Text #17

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1041. Min Act: -0.0000

Data Index: 883051 (C4 (Web Text))

Max Activating Token Index: 1020

Text #18

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1128. Min Act: -0.0000

Data Index: 220923 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 0.1341. Min Range: -0.1341

Max Act: 0.1038. Min Act: -0.0001

Data Index: 869396 (C4 (Web Text))

Max Activating Token Index: 877