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

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

Neuron 840 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1538. Min Act: -0.0001

Data Index: 751031 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1267. Min Act: -0.0001

Data Index: 970676 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1347. Min Act: -0.0001

Data Index: 420529 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1180. Min Act: -0.0001

Data Index: 865809 (C4 (Web Text))

Max Activating Token Index: 238

Text #4

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1190. Min Act: -0.0001

Data Index: 246998 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1165. Min Act: -0.0001

Data Index: 160220 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1168. Min Act: -0.0001

Data Index: 880083 (C4 (Web Text))

Max Activating Token Index: 450

Text #7

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1059. Min Act: -0.0001

Data Index: 661171 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1101. Min Act: -0.0001

Data Index: 501579 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1136. Min Act: -0.0001

Data Index: 54537 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1083. Min Act: -0.0001

Data Index: 666539 (C4 (Web Text))

Max Activating Token Index: 171

Text #11

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1113. Min Act: -0.0001

Data Index: 909952 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1116. Min Act: -0.0001

Data Index: 527823 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1100. Min Act: -0.0001

Data Index: 1290800 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1053. Min Act: -0.0001

Data Index: 912944 (C4 (Web Text))

Max Activating Token Index: 212

Text #15

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1085. Min Act: -0.0001

Data Index: 389813 (C4 (Web Text))

Max Activating Token Index: 445

Text #16

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1074. Min Act: -0.0001

Data Index: 158514 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1071. Min Act: -0.0001

Data Index: 1326820 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1029. Min Act: -0.0001

Data Index: 1352261 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1237. Min Act: -0.0001

Data Index: 46426 (C4 (Web Text))

Max Activating Token Index: 737