Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 632 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1258. Min Act: -0.0001

Data Index: 531691 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1166. Min Act: -0.0001

Data Index: 883730 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1113. Min Act: -0.0001

Data Index: 926538 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1140. Min Act: -0.0001

Data Index: 809658 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1172. Min Act: -0.0001

Data Index: 1088648 (C4 (Web Text))

Max Activating Token Index: 608

Text #5

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1078. Min Act: -0.0001

Data Index: 81117 (C4 (Web Text))

Max Activating Token Index: 153

Text #6

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1050. Min Act: -0.0001

Data Index: 539714 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1070. Min Act: -0.0001

Data Index: 191750 (C4 (Web Text))

Max Activating Token Index: 230

Text #8

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1058. Min Act: -0.0001

Data Index: 842152 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0965. Min Act: -0.0001

Data Index: 1173707 (C4 (Web Text))

Max Activating Token Index: 905

Text #10

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1025. Min Act: -0.0001

Data Index: 455398 (C4 (Web Text))

Max Activating Token Index: 358

Text #11

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1008. Min Act: -0.0001

Data Index: 1046750 (C4 (Web Text))

Max Activating Token Index: 187

Text #12

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1066. Min Act: -0.0001

Data Index: 1277178 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0976. Min Act: -0.0001

Data Index: 281463 (C4 (Web Text))

Max Activating Token Index: 913

Text #14

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1005. Min Act: -0.0001

Data Index: 650789 (C4 (Web Text))

Max Activating Token Index: 493

Text #15

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1028. Min Act: -0.0001

Data Index: 937991 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1017. Min Act: -0.0001

Data Index: 1256919 (C4 (Web Text))

Max Activating Token Index: 67

Text #17

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1056. Min Act: -0.0001

Data Index: 13756 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1015. Min Act: -0.0001

Data Index: 601292 (C4 (Web Text))

Max Activating Token Index: 656

Text #19

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0919. Min Act: -0.0001

Data Index: 793412 (C4 (Web Text))

Max Activating Token Index: 876