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

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

Neuron 3204 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: 0.1255. Min Range: -0.1255

Max Act: 0.1076. Min Act: -0.0000

Data Index: 862046 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1255. Min Act: -0.0000

Data Index: 584135 (C4 (Web Text))

Max Activating Token Index: 863

Text #2

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1172. Min Act: -0.0000

Data Index: 1221549 (C4 (Web Text))

Max Activating Token Index: 537

Text #3

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1075. Min Act: -0.0000

Data Index: 231266 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1089. Min Act: -0.0001

Data Index: 798246 (C4 (Web Text))

Max Activating Token Index: 452

Text #5

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0911. Min Act: -0.0000

Data Index: 613918 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1055. Min Act: -0.0000

Data Index: 652089 (C4 (Web Text))

Max Activating Token Index: 613

Text #7

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1086. Min Act: -0.0000

Data Index: 867155 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1074. Min Act: -0.0001

Data Index: 1041427 (C4 (Web Text))

Max Activating Token Index: 62

Text #9

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1057. Min Act: -0.0000

Data Index: 1054109 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1050. Min Act: -0.0000

Data Index: 317429 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0971. Min Act: -0.0000

Data Index: 1099479 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0922. Min Act: -0.0001

Data Index: 855738 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0981. Min Act: -0.0000

Data Index: 338658 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.1056. Min Act: -0.0000

Data Index: 913501 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0907. Min Act: -0.0000

Data Index: 964606 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0848. Min Act: -0.0000

Data Index: 1040844 (C4 (Web Text))

Max Activating Token Index: 249

Text #17

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0898. Min Act: -0.0000

Data Index: 676295 (C4 (Web Text))

Max Activating Token Index: 773

Text #18

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0979. Min Act: -0.0000

Data Index: 230038 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 0.1255. Min Range: -0.1255

Max Act: 0.0854. Min Act: -0.0000

Data Index: 770223 (C4 (Web Text))

Max Activating Token Index: 304