Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2791 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1490. Min Act: -0.0000

Data Index: 1319643 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1492. Min Act: -0.0001

Data Index: 603160 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1214. Min Act: -0.0000

Data Index: 120895 (C4 (Web Text))

Max Activating Token Index: 443

Text #3

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1217. Min Act: -0.0001

Data Index: 726709 (C4 (Web Text))

Max Activating Token Index: 738

Text #4

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1208. Min Act: -0.0001

Data Index: 625187 (C4 (Web Text))

Max Activating Token Index: 439

Text #5

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1146. Min Act: -0.0000

Data Index: 49502 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1144. Min Act: -0.0001

Data Index: 916419 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1129. Min Act: -0.0001

Data Index: 207591 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1154. Min Act: -0.0001

Data Index: 176467 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1070. Min Act: -0.0001

Data Index: 117365 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1089. Min Act: -0.0001

Data Index: 32894 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1100. Min Act: -0.0001

Data Index: 1226122 (C4 (Web Text))

Max Activating Token Index: 439

Text #12

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1056. Min Act: -0.0001

Data Index: 193951 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1043. Min Act: -0.0000

Data Index: 552706 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1114. Min Act: -0.0000

Data Index: 647088 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1030. Min Act: -0.0000

Data Index: 1218945 (C4 (Web Text))

Max Activating Token Index: 230

Text #16

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1038. Min Act: -0.0001

Data Index: 665818 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1031. Min Act: -0.0000

Data Index: 1055605 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1037. Min Act: -0.0000

Data Index: 491137 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 0.1492. Min Range: -0.1492

Max Act: 0.1113. Min Act: -0.0001

Data Index: 459142 (C4 (Web Text))

Max Activating Token Index: 396