Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3018 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1574. Min Act: -0.0000

Data Index: 942421 (C4 (Web Text))

Max Activating Token Index: 582

Text #1

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1400. Min Act: -0.0000

Data Index: 439983 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1304. Min Act: -0.0000

Data Index: 684369 (C4 (Web Text))

Max Activating Token Index: 369

Text #3

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1346. Min Act: -0.0000

Data Index: 783369 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1146. Min Act: -0.0000

Data Index: 577076 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1121. Min Act: -0.0000

Data Index: 534234 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1108. Min Act: -0.0000

Data Index: 1156204 (C4 (Web Text))

Max Activating Token Index: 449

Text #7

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1129. Min Act: -0.0000

Data Index: 1287804 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1102. Min Act: -0.0000

Data Index: 1234929 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1090. Min Act: -0.0000

Data Index: 486368 (C4 (Web Text))

Max Activating Token Index: 313

Text #10

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1075. Min Act: -0.0000

Data Index: 629326 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1040. Min Act: -0.0000

Data Index: 739124 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1064. Min Act: -0.0000

Data Index: 130363 (C4 (Web Text))

Max Activating Token Index: 379

Text #13

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.0951. Min Act: -0.0000

Data Index: 442341 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1049. Min Act: -0.0000

Data Index: 560286 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1059. Min Act: -0.0000

Data Index: 921996 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1046. Min Act: -0.0000

Data Index: 274999 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1037. Min Act: -0.0000

Data Index: 1068433 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1034. Min Act: -0.0000

Data Index: 774548 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 0.1574. Min Range: -0.1574

Max Act: 0.1001. Min Act: -0.0000

Data Index: 1221786 (C4 (Web Text))

Max Activating Token Index: 208