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

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

Neuron 882 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: 0.1515. Min Range: -0.1515

Max Act: 0.1515. Min Act: -0.0001

Data Index: 897150 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1340. Min Act: -0.0001

Data Index: 685875 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1271. Min Act: -0.0001

Data Index: 746418 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1218. Min Act: -0.0001

Data Index: 781126 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1120. Min Act: -0.0000

Data Index: 605791 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1191. Min Act: -0.0001

Data Index: 890059 (C4 (Web Text))

Max Activating Token Index: 301

Text #6

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1156. Min Act: -0.0001

Data Index: 1271692 (C4 (Web Text))

Max Activating Token Index: 246

Text #7

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1157. Min Act: -0.0001

Data Index: 1281994 (C4 (Web Text))

Max Activating Token Index: 558

Text #8

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1136. Min Act: -0.0001

Data Index: 653252 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1106. Min Act: -0.0001

Data Index: 1321253 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1126. Min Act: -0.0001

Data Index: 1125890 (C4 (Web Text))

Max Activating Token Index: 549

Text #11

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1118. Min Act: -0.0001

Data Index: 868223 (C4 (Web Text))

Max Activating Token Index: 484

Text #12

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1103. Min Act: -0.0001

Data Index: 371704 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1100. Min Act: -0.0001

Data Index: 528259 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1080. Min Act: -0.0001

Data Index: 363745 (C4 (Web Text))

Max Activating Token Index: 999

Text #15

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1044. Min Act: -0.0001

Data Index: 788083 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1072. Min Act: -0.0001

Data Index: 141170 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1053. Min Act: -0.0001

Data Index: 554579 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1014. Min Act: -0.0001

Data Index: 1193447 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 0.1515. Min Range: -0.1515

Max Act: 0.1056. Min Act: -0.0001

Data Index: 868452 (C4 (Web Text))

Max Activating Token Index: 975