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

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

Neuron 1330 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: 0.1287. Min Range: -0.1287

Max Act: 0.1103. Min Act: -0.0001

Data Index: 862698 (C4 (Web Text))

Max Activating Token Index: 663

Text #1

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1287. Min Act: -0.0001

Data Index: 625859 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1284. Min Act: -0.0001

Data Index: 599012 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1223. Min Act: -0.0001

Data Index: 1230530 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1073. Min Act: -0.0001

Data Index: 589841 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1257. Min Act: -0.0001

Data Index: 170758 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1039. Min Act: -0.0001

Data Index: 266102 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1094. Min Act: -0.0001

Data Index: 294944 (C4 (Web Text))

Max Activating Token Index: 871

Text #8

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.0978. Min Act: -0.0001

Data Index: 599198 (C4 (Web Text))

Max Activating Token Index: 752

Text #9

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1059. Min Act: -0.0001

Data Index: 682112 (C4 (Web Text))

Max Activating Token Index: 777

Text #10

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1024. Min Act: -0.0001

Data Index: 182726 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1102. Min Act: -0.0001

Data Index: 447334 (C4 (Web Text))

Max Activating Token Index: 858

Text #12

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.0860. Min Act: -0.0001

Data Index: 194024 (C4 (Web Text))

Max Activating Token Index: 919

Text #13

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.0974. Min Act: -0.0001

Data Index: 745283 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1016. Min Act: -0.0001

Data Index: 80374 (C4 (Web Text))

Max Activating Token Index: 857

Text #15

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1046. Min Act: -0.0001

Data Index: 773540 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1006. Min Act: -0.0001

Data Index: 1099643 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.0988. Min Act: -0.0001

Data Index: 626208 (C4 (Web Text))

Max Activating Token Index: 867

Text #18

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.0944. Min Act: -0.0001

Data Index: 954143 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.0976. Min Act: -0.0001

Data Index: 164817 (C4 (Web Text))

Max Activating Token Index: 1020