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

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

Neuron 6025 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1432. Min Act: -0.0002

Data Index: 551712 (C4 (Web Text))

Max Activating Token Index: 360

Text #1

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1482. Min Act: -0.0002

Data Index: 883293 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1443. Min Act: -0.0002

Data Index: 257139 (C4 (Web Text))

Max Activating Token Index: 546

Text #3

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1406. Min Act: -0.0002

Data Index: 1653828 (Python Code)

Max Activating Token Index: 99

Text #4

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1354. Min Act: -0.0002

Data Index: 469254 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1308. Min Act: -0.0002

Data Index: 72931 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1156. Min Act: -0.0002

Data Index: 178769 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1050. Min Act: -0.0002

Data Index: 702653 (C4 (Web Text))

Max Activating Token Index: 361

Text #8

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1030. Min Act: -0.0002

Data Index: 1555538 (Python Code)

Max Activating Token Index: 184

Text #9

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1020. Min Act: -0.0002

Data Index: 1045640 (C4 (Web Text))

Max Activating Token Index: 289

Text #10

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1025. Min Act: -0.0002

Data Index: 733722 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1026. Min Act: -0.0002

Data Index: 747881 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1055. Min Act: -0.0002

Data Index: 378542 (C4 (Web Text))

Max Activating Token Index: 475

Text #13

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1045. Min Act: -0.0002

Data Index: 1275196 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1028. Min Act: -0.0002

Data Index: 642694 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0985. Min Act: -0.0002

Data Index: 101813 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0951. Min Act: -0.0002

Data Index: 895946 (C4 (Web Text))

Max Activating Token Index: 478

Text #17

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1013. Min Act: -0.0002

Data Index: 119561 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0984. Min Act: -0.0002

Data Index: 1026791 (C4 (Web Text))

Max Activating Token Index: 441

Text #19

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0944. Min Act: -0.0002

Data Index: 872034 (C4 (Web Text))

Max Activating Token Index: 170