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

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

Neuron 1096 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: 0.1147. Min Range: -0.1147

Max Act: 0.1147. Min Act: -0.0001

Data Index: 257989 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1125. Min Act: -0.0001

Data Index: 1235887 (C4 (Web Text))

Max Activating Token Index: 1010

Text #2

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1080. Min Act: -0.0001

Data Index: 1063973 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1102. Min Act: -0.0001

Data Index: 890558 (C4 (Web Text))

Max Activating Token Index: 489

Text #4

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1060. Min Act: -0.0001

Data Index: 928948 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1080. Min Act: -0.0001

Data Index: 930082 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1040. Min Act: -0.0001

Data Index: 281920 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1073. Min Act: -0.0001

Data Index: 25538 (C4 (Web Text))

Max Activating Token Index: 1007

Text #8

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1067. Min Act: -0.0001

Data Index: 382889 (C4 (Web Text))

Max Activating Token Index: 530

Text #9

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1029. Min Act: -0.0001

Data Index: 420143 (C4 (Web Text))

Max Activating Token Index: 708

Text #10

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1100. Min Act: -0.0001

Data Index: 1189910 (C4 (Web Text))

Max Activating Token Index: 286

Text #11

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1064. Min Act: -0.0001

Data Index: 765868 (C4 (Web Text))

Max Activating Token Index: 339

Text #12

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1105. Min Act: -0.0001

Data Index: 813765 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1019. Min Act: -0.0001

Data Index: 632332 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1052. Min Act: -0.0001

Data Index: 52141 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1052. Min Act: -0.0001

Data Index: 914779 (C4 (Web Text))

Max Activating Token Index: 679

Text #16

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1023. Min Act: -0.0001

Data Index: 1315561 (C4 (Web Text))

Max Activating Token Index: 639

Text #17

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1048. Min Act: -0.0001

Data Index: 341283 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1047. Min Act: -0.0001

Data Index: 1008191 (C4 (Web Text))

Max Activating Token Index: 995

Text #19

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1040. Min Act: -0.0001

Data Index: 694562 (C4 (Web Text))

Max Activating Token Index: 645