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

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

Neuron 2591 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1487. Min Act: -0.0001

Data Index: 1007251 (C4 (Web Text))

Max Activating Token Index: 337

Text #1

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1287. Min Act: -0.0001

Data Index: 1090233 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1132. Min Act: -0.0001

Data Index: 1043126 (C4 (Web Text))

Max Activating Token Index: 317

Text #3

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1340. Min Act: -0.0001

Data Index: 1222651 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1117. Min Act: -0.0001

Data Index: 177804 (C4 (Web Text))

Max Activating Token Index: 964

Text #5

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1209. Min Act: -0.0001

Data Index: 13381 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1228. Min Act: -0.0001

Data Index: 53390 (C4 (Web Text))

Max Activating Token Index: 283

Text #7

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1221. Min Act: -0.0001

Data Index: 441745 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1098. Min Act: -0.0001

Data Index: 605492 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1134. Min Act: -0.0001

Data Index: 832902 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1169. Min Act: -0.0002

Data Index: 861084 (C4 (Web Text))

Max Activating Token Index: 989

Text #11

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1164. Min Act: -0.0001

Data Index: 1202356 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1049. Min Act: -0.0001

Data Index: 1289103 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1077. Min Act: -0.0001

Data Index: 1225381 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1144. Min Act: -0.0001

Data Index: 404675 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1128. Min Act: -0.0001

Data Index: 1235476 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1013. Min Act: -0.0001

Data Index: 16191 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1015. Min Act: -0.0001

Data Index: 895541 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1129. Min Act: -0.0001

Data Index: 529790 (C4 (Web Text))

Max Activating Token Index: 343

Text #19

Max Range: 0.1487. Min Range: -0.1487

Max Act: 0.1049. Min Act: -0.0001

Data Index: 967037 (C4 (Web Text))

Max Activating Token Index: 83