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

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

Neuron 867 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1430. Min Act: -0.0001

Data Index: 358143 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1326. Min Act: -0.0001

Data Index: 519701 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1273. Min Act: -0.0001

Data Index: 963248 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1235. Min Act: -0.0001

Data Index: 1137916 (C4 (Web Text))

Max Activating Token Index: 643

Text #4

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1214. Min Act: -0.0001

Data Index: 319552 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1087. Min Act: -0.0001

Data Index: 622878 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.0987. Min Act: -0.0001

Data Index: 530090 (C4 (Web Text))

Max Activating Token Index: 601

Text #7

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1028. Min Act: -0.0001

Data Index: 15284 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1054. Min Act: -0.0001

Data Index: 1047531 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1089. Min Act: -0.0001

Data Index: 1199427 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1015. Min Act: -0.0001

Data Index: 471149 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1036. Min Act: -0.0001

Data Index: 206744 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1047. Min Act: -0.0001

Data Index: 237079 (C4 (Web Text))

Max Activating Token Index: 684

Text #13

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1117. Min Act: -0.0001

Data Index: 934926 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1113. Min Act: -0.0001

Data Index: 947018 (C4 (Web Text))

Max Activating Token Index: 941

Text #15

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1071. Min Act: -0.0001

Data Index: 985888 (C4 (Web Text))

Max Activating Token Index: 701

Text #16

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1030. Min Act: -0.0001

Data Index: 940388 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1024. Min Act: -0.0001

Data Index: 458350 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1068. Min Act: -0.0001

Data Index: 93463 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1054. Min Act: -0.0001

Data Index: 1252470 (C4 (Web Text))

Max Activating Token Index: 24