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

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

Neuron 3020 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1159. Min Act: -0.0001

Data Index: 739922 (C4 (Web Text))

Max Activating Token Index: 247

Text #1

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1183. Min Act: -0.0001

Data Index: 67799 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1141. Min Act: -0.0001

Data Index: 1259975 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1139. Min Act: -0.0001

Data Index: 379728 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1090. Min Act: -0.0001

Data Index: 846492 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1163. Min Act: -0.0001

Data Index: 980268 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1108. Min Act: -0.0001

Data Index: 613550 (C4 (Web Text))

Max Activating Token Index: 830

Text #7

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1063. Min Act: -0.0001

Data Index: 948402 (C4 (Web Text))

Max Activating Token Index: 940

Text #8

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1022. Min Act: -0.0001

Data Index: 144564 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1084. Min Act: -0.0001

Data Index: 1281486 (C4 (Web Text))

Max Activating Token Index: 747

Text #10

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1078. Min Act: -0.0001

Data Index: 812768 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0910. Min Act: -0.0001

Data Index: 1082032 (C4 (Web Text))

Max Activating Token Index: 594

Text #12

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0983. Min Act: -0.0001

Data Index: 727769 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1014. Min Act: -0.0001

Data Index: 1086867 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1007. Min Act: -0.0001

Data Index: 154004 (C4 (Web Text))

Max Activating Token Index: 831

Text #15

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1032. Min Act: -0.0001

Data Index: 310076 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1078. Min Act: -0.0001

Data Index: 186949 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1012. Min Act: -0.0001

Data Index: 82278 (C4 (Web Text))

Max Activating Token Index: 602

Text #18

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1005. Min Act: -0.0001

Data Index: 654174 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1029. Min Act: -0.0001

Data Index: 15574 (C4 (Web Text))

Max Activating Token Index: 447