Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3738 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1230. Min Act: -0.0001

Data Index: 1095630 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1284. Min Act: -0.0001

Data Index: 610728 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1192. Min Act: -0.0001

Data Index: 654425 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1199. Min Act: -0.0001

Data Index: 752518 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1264. Min Act: -0.0001

Data Index: 379344 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1160. Min Act: -0.0001

Data Index: 377971 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1029. Min Act: -0.0001

Data Index: 1137344 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1119. Min Act: -0.0001

Data Index: 949929 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1240. Min Act: -0.0001

Data Index: 340997 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1158. Min Act: -0.0001

Data Index: 210791 (C4 (Web Text))

Max Activating Token Index: 944

Text #10

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1084. Min Act: -0.0001

Data Index: 353045 (C4 (Web Text))

Max Activating Token Index: 967

Text #11

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1080. Min Act: -0.0001

Data Index: 306629 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1023. Min Act: -0.0001

Data Index: 1064085 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1046. Min Act: -0.0001

Data Index: 1037298 (C4 (Web Text))

Max Activating Token Index: 799

Text #14

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0952. Min Act: -0.0001

Data Index: 1310318 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0891. Min Act: -0.0001

Data Index: 492790 (C4 (Web Text))

Max Activating Token Index: 413

Text #16

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0950. Min Act: -0.0001

Data Index: 318307 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0897. Min Act: -0.0001

Data Index: 1106457 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0966. Min Act: -0.0001

Data Index: 186144 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1006. Min Act: -0.0001

Data Index: 214307 (C4 (Web Text))

Max Activating Token Index: 998