Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 164 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1674. Min Act: -0.0001

Data Index: 874736 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1488. Min Act: -0.0001

Data Index: 56529 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1298. Min Act: -0.0001

Data Index: 557497 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1282. Min Act: -0.0001

Data Index: 1144798 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1201. Min Act: -0.0001

Data Index: 927463 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1156. Min Act: -0.0001

Data Index: 1098055 (C4 (Web Text))

Max Activating Token Index: 281

Text #6

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1144. Min Act: -0.0001

Data Index: 32084 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1192. Min Act: -0.0001

Data Index: 1348189 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1194. Min Act: -0.0001

Data Index: 249066 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1141. Min Act: -0.0000

Data Index: 753406 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1140. Min Act: -0.0001

Data Index: 584613 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1181. Min Act: -0.0001

Data Index: 394133 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1183. Min Act: -0.0001

Data Index: 900716 (C4 (Web Text))

Max Activating Token Index: 866

Text #13

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1129. Min Act: -0.0001

Data Index: 641162 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1109. Min Act: -0.0001

Data Index: 715638 (C4 (Web Text))

Max Activating Token Index: 590

Text #15

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1184. Min Act: -0.0001

Data Index: 394589 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1059. Min Act: -0.0001

Data Index: 843969 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1096. Min Act: -0.0001

Data Index: 578381 (C4 (Web Text))

Max Activating Token Index: 41

Text #18

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1019. Min Act: -0.0001

Data Index: 422778 (C4 (Web Text))

Max Activating Token Index: 832

Text #19

Max Range: 0.1674. Min Range: -0.1674

Max Act: 0.1006. Min Act: -0.0001

Data Index: 394211 (C4 (Web Text))

Max Activating Token Index: 799