Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3340 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1768. Min Act: -0.0000

Data Index: 961775 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1540. Min Act: -0.0001

Data Index: 1257607 (C4 (Web Text))

Max Activating Token Index: 771

Text #2

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1344. Min Act: -0.0000

Data Index: 258545 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1425. Min Act: -0.0000

Data Index: 1065171 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1216. Min Act: -0.0000

Data Index: 1081149 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1073. Min Act: -0.0000

Data Index: 201724 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1079. Min Act: -0.0000

Data Index: 384756 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1097. Min Act: -0.0001

Data Index: 477615 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1072. Min Act: -0.0000

Data Index: 1116438 (C4 (Web Text))

Max Activating Token Index: 583

Text #9

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1219. Min Act: -0.0001

Data Index: 717144 (C4 (Web Text))

Max Activating Token Index: 403

Text #10

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1066. Min Act: -0.0000

Data Index: 843666 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1015. Min Act: -0.0001

Data Index: 1340527 (C4 (Web Text))

Max Activating Token Index: 405

Text #12

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1088. Min Act: -0.0000

Data Index: 886857 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1104. Min Act: -0.0000

Data Index: 524542 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1068. Min Act: -0.0000

Data Index: 1065467 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1148. Min Act: -0.0000

Data Index: 790124 (C4 (Web Text))

Max Activating Token Index: 842

Text #16

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1043. Min Act: -0.0000

Data Index: 1025795 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.0990. Min Act: -0.0000

Data Index: 446680 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1036. Min Act: -0.0000

Data Index: 826264 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1022. Min Act: -0.0000

Data Index: 1188903 (C4 (Web Text))

Max Activating Token Index: 598