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

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

Neuron 33 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1151. Min Act: -0.0003

Data Index: 625189 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1156. Min Act: -0.0003

Data Index: 503666 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1137. Min Act: -0.0003

Data Index: 51309 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1140. Min Act: -0.0003

Data Index: 1300055 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1039. Min Act: -0.0003

Data Index: 845437 (C4 (Web Text))

Max Activating Token Index: 954

Text #5

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1102. Min Act: -0.0003

Data Index: 464677 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1151. Min Act: -0.0003

Data Index: 376733 (C4 (Web Text))

Max Activating Token Index: 515

Text #7

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1070. Min Act: -0.0003

Data Index: 996189 (C4 (Web Text))

Max Activating Token Index: 683

Text #8

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1135. Min Act: -0.0003

Data Index: 389789 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1098. Min Act: -0.0003

Data Index: 680541 (C4 (Web Text))

Max Activating Token Index: 949

Text #10

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0938. Min Act: -0.0003

Data Index: 1242257 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1060. Min Act: -0.0003

Data Index: 71836 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1072. Min Act: -0.0003

Data Index: 1122841 (C4 (Web Text))

Max Activating Token Index: 711

Text #13

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1055. Min Act: -0.0003

Data Index: 195765 (C4 (Web Text))

Max Activating Token Index: 877

Text #14

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1009. Min Act: -0.0003

Data Index: 312995 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1077. Min Act: -0.0003

Data Index: 449580 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1036. Min Act: -0.0003

Data Index: 522010 (C4 (Web Text))

Max Activating Token Index: 803

Text #17

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0916. Min Act: -0.0003

Data Index: 121264 (C4 (Web Text))

Max Activating Token Index: 395

Text #18

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1195. Min Act: -0.0003

Data Index: 158223 (C4 (Web Text))

Max Activating Token Index: 481

Text #19

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0987. Min Act: -0.0003

Data Index: 1198325 (C4 (Web Text))

Max Activating Token Index: 825