Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3339 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1416. Min Act: -0.0002

Data Index: 116623 (C4 (Web Text))

Max Activating Token Index: 308

Text #1

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1290. Min Act: -0.0002

Data Index: 461713 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1172. Min Act: -0.0001

Data Index: 1137862 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1135. Min Act: -0.0002

Data Index: 58423 (C4 (Web Text))

Max Activating Token Index: 975

Text #4

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1053. Min Act: -0.0002

Data Index: 879700 (C4 (Web Text))

Max Activating Token Index: 864

Text #5

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1151. Min Act: -0.0002

Data Index: 416796 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1189. Min Act: -0.0001

Data Index: 1351291 (C4 (Web Text))

Max Activating Token Index: 472

Text #7

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1270. Min Act: -0.0002

Data Index: 495543 (C4 (Web Text))

Max Activating Token Index: 158

Text #8

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1121. Min Act: -0.0002

Data Index: 707479 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1136. Min Act: -0.0001

Data Index: 702553 (C4 (Web Text))

Max Activating Token Index: 91

Text #10

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1131. Min Act: -0.0001

Data Index: 375805 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1172. Min Act: -0.0002

Data Index: 1316236 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1162. Min Act: -0.0002

Data Index: 417905 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1090. Min Act: -0.0001

Data Index: 264453 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1057. Min Act: -0.0001

Data Index: 802360 (C4 (Web Text))

Max Activating Token Index: 289

Text #15

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1173. Min Act: -0.0002

Data Index: 676861 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1123. Min Act: -0.0001

Data Index: 1139734 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1114. Min Act: -0.0002

Data Index: 1083407 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1093. Min Act: -0.0002

Data Index: 451261 (C4 (Web Text))

Max Activating Token Index: 529

Text #19

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1102. Min Act: -0.0002

Data Index: 40599 (C4 (Web Text))

Max Activating Token Index: 768