Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1310 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1224. Min Act: -0.0003

Data Index: 887711 (C4 (Web Text))

Max Activating Token Index: 818

Text #1

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1115. Min Act: -0.0003

Data Index: 772976 (C4 (Web Text))

Max Activating Token Index: 984

Text #2

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1125. Min Act: -0.0003

Data Index: 419126 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1110. Min Act: -0.0003

Data Index: 967724 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1085. Min Act: -0.0003

Data Index: 1134460 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1033. Min Act: -0.0003

Data Index: 328274 (C4 (Web Text))

Max Activating Token Index: 707

Text #6

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1073. Min Act: -0.0003

Data Index: 839132 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1105. Min Act: -0.0003

Data Index: 680105 (C4 (Web Text))

Max Activating Token Index: 431

Text #8

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1106. Min Act: -0.0004

Data Index: 1339036 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1058. Min Act: -0.0003

Data Index: 122359 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1073. Min Act: -0.0003

Data Index: 352491 (C4 (Web Text))

Max Activating Token Index: 300

Text #11

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1020. Min Act: -0.0003

Data Index: 164421 (C4 (Web Text))

Max Activating Token Index: 522

Text #12

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1020. Min Act: -0.0003

Data Index: 462938 (C4 (Web Text))

Max Activating Token Index: 871

Text #13

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1029. Min Act: -0.0003

Data Index: 771201 (C4 (Web Text))

Max Activating Token Index: 502

Text #14

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0995. Min Act: -0.0003

Data Index: 429299 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0994. Min Act: -0.0003

Data Index: 514106 (C4 (Web Text))

Max Activating Token Index: 237

Text #16

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0969. Min Act: -0.0003

Data Index: 1049010 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0983. Min Act: -0.0003

Data Index: 1142607 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1008. Min Act: -0.0003

Data Index: 285956 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1007. Min Act: -0.0003

Data Index: 284897 (C4 (Web Text))

Max Activating Token Index: 765