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

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

Neuron 3263 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4196. Min Range: -3.4196

Max Act: 3.4196. Min Act: -0.0000

Data Index: 43530 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 3.4196. Min Range: -3.4196

Max Act: 2.7468. Min Act: -0.0000

Data Index: 470689 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 3.4196. Min Range: -3.4196

Max Act: 2.7911. Min Act: -0.0000

Data Index: 585974 (C4 (Web Text))

Max Activating Token Index: 604

Text #3

Max Range: 3.4196. Min Range: -3.4196

Max Act: 2.8077. Min Act: -0.0000

Data Index: 464636 (C4 (Web Text))

Max Activating Token Index: 739

Text #4

Max Range: 3.4196. Min Range: -3.4196

Max Act: 2.3754. Min Act: -0.0000

Data Index: 920391 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 3.4196. Min Range: -3.4196

Max Act: 2.1555. Min Act: -0.0000

Data Index: 1068047 (C4 (Web Text))

Max Activating Token Index: 812

Text #6

Max Range: 3.4196. Min Range: -3.4196

Max Act: 2.2209. Min Act: -0.0000

Data Index: 331032 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 3.4196. Min Range: -3.4196

Max Act: 2.0496. Min Act: -0.0000

Data Index: 291224 (C4 (Web Text))

Max Activating Token Index: 460

Text #8

Max Range: 3.4196. Min Range: -3.4196

Max Act: 2.0023. Min Act: -0.0000

Data Index: 1153870 (C4 (Web Text))

Max Activating Token Index: 626

Text #9

Max Range: 3.4196. Min Range: -3.4196

Max Act: 1.9891. Min Act: -0.0000

Data Index: 584013 (C4 (Web Text))

Max Activating Token Index: 735

Text #10

Max Range: 3.4196. Min Range: -3.4196

Max Act: 1.7876. Min Act: -0.0000

Data Index: 61126 (C4 (Web Text))

Max Activating Token Index: 761

Text #11

Max Range: 3.4196. Min Range: -3.4196

Max Act: 1.8693. Min Act: -0.0000

Data Index: 501363 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 3.4196. Min Range: -3.4196

Max Act: 1.7733. Min Act: -0.0000

Data Index: 970500 (C4 (Web Text))

Max Activating Token Index: 566

Text #13

Max Range: 3.4196. Min Range: -3.4196

Max Act: 1.9535. Min Act: -0.0000

Data Index: 792560 (C4 (Web Text))

Max Activating Token Index: 309

Text #14

Max Range: 3.4196. Min Range: -3.4196

Max Act: 1.7612. Min Act: -0.0000

Data Index: 1338843 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 3.4196. Min Range: -3.4196

Max Act: 1.8336. Min Act: -0.0000

Data Index: 926503 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 3.4196. Min Range: -3.4196

Max Act: 1.7558. Min Act: -0.0000

Data Index: 1025186 (C4 (Web Text))

Max Activating Token Index: 478

Text #17

Max Range: 3.4196. Min Range: -3.4196

Max Act: 1.6972. Min Act: -0.0000

Data Index: 993467 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 3.4196. Min Range: -3.4196

Max Act: 1.8646. Min Act: -0.0000

Data Index: 865730 (C4 (Web Text))

Max Activating Token Index: 706

Text #19

Max Range: 3.4196. Min Range: -3.4196

Max Act: 1.6574. Min Act: -0.0000

Data Index: 546965 (C4 (Web Text))

Max Activating Token Index: 925