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

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

Neuron 1440 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2459. Min Act: -0.0000

Data Index: 350491 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2010. Min Act: -0.0000

Data Index: 619968 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1802. Min Act: -0.0000

Data Index: 129081 (C4 (Web Text))

Max Activating Token Index: 989

Text #3

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1849. Min Act: -0.0000

Data Index: 239990 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1386. Min Act: -0.0000

Data Index: 1077970 (C4 (Web Text))

Max Activating Token Index: 678

Text #5

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1047. Min Act: -0.0000

Data Index: 311039 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1191. Min Act: -0.0000

Data Index: 36282 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1224. Min Act: -0.0000

Data Index: 1115485 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1264. Min Act: -0.0000

Data Index: 261963 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1103. Min Act: -0.0000

Data Index: 1023547 (C4 (Web Text))

Max Activating Token Index: 347

Text #10

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1073. Min Act: -0.0000

Data Index: 141013 (C4 (Web Text))

Max Activating Token Index: 794

Text #11

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1082. Min Act: -0.0000

Data Index: 806148 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1126. Min Act: -0.0000

Data Index: 612201 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1144. Min Act: -0.0000

Data Index: 950342 (C4 (Web Text))

Max Activating Token Index: 412

Text #14

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1061. Min Act: -0.0000

Data Index: 22357 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1126. Min Act: -0.0000

Data Index: 239169 (C4 (Web Text))

Max Activating Token Index: 509

Text #16

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1112. Min Act: -0.0000

Data Index: 1181357 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1085. Min Act: -0.0000

Data Index: 1153151 (C4 (Web Text))

Max Activating Token Index: 292

Text #18

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1030. Min Act: -0.0000

Data Index: 1045890 (C4 (Web Text))

Max Activating Token Index: 284

Text #19

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1138. Min Act: -0.0000

Data Index: 1263477 (C4 (Web Text))

Max Activating Token Index: 544