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

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

Neuron 221 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: 0.1362. Min Range: -0.1362

Max Act: 0.1362. Min Act: -0.0001

Data Index: 1059825 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1172. Min Act: -0.0002

Data Index: 631248 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1167. Min Act: -0.0002

Data Index: 489047 (C4 (Web Text))

Max Activating Token Index: 619

Text #3

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1135. Min Act: -0.0001

Data Index: 642445 (C4 (Web Text))

Max Activating Token Index: 769

Text #4

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1136. Min Act: -0.0001

Data Index: 17130 (C4 (Web Text))

Max Activating Token Index: 70

Text #5

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1166. Min Act: -0.0001

Data Index: 848639 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1106. Min Act: -0.0002

Data Index: 918214 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1081. Min Act: -0.0002

Data Index: 133009 (C4 (Web Text))

Max Activating Token Index: 414

Text #8

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1040. Min Act: -0.0002

Data Index: 1057669 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1046. Min Act: -0.0002

Data Index: 242229 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1092. Min Act: -0.0002

Data Index: 687218 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1049. Min Act: -0.0002

Data Index: 1343783 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1051. Min Act: -0.0002

Data Index: 254540 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1038. Min Act: -0.0002

Data Index: 525350 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1053. Min Act: -0.0001

Data Index: 1188137 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1031. Min Act: -0.0001

Data Index: 293096 (C4 (Web Text))

Max Activating Token Index: 241

Text #16

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1006. Min Act: -0.0002

Data Index: 1290588 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1048. Min Act: -0.0002

Data Index: 1267913 (C4 (Web Text))

Max Activating Token Index: 593

Text #18

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1004. Min Act: -0.0002

Data Index: 69354 (C4 (Web Text))

Max Activating Token Index: 649

Text #19

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.0955. Min Act: -0.0001

Data Index: 196307 (C4 (Web Text))

Max Activating Token Index: 813