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

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

Neuron 3674 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0699. Min Act: -0.0003

Data Index: 1100689 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0569. Min Act: -0.0003

Data Index: 902055 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0556. Min Act: -0.0003

Data Index: 1175473 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0523. Min Act: -0.0003

Data Index: 383932 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0516. Min Act: -0.0003

Data Index: 425311 (C4 (Web Text))

Max Activating Token Index: 439

Text #5

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0509. Min Act: -0.0003

Data Index: 677357 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0485. Min Act: -0.0003

Data Index: 928860 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0477. Min Act: -0.0003

Data Index: 414136 (C4 (Web Text))

Max Activating Token Index: 554

Text #8

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0485. Min Act: -0.0003

Data Index: 775561 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0472. Min Act: -0.0002

Data Index: 531583 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0479. Min Act: -0.0003

Data Index: 1314212 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0467. Min Act: -0.0003

Data Index: 717934 (C4 (Web Text))

Max Activating Token Index: 860

Text #12

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0454. Min Act: -0.0003

Data Index: 495539 (C4 (Web Text))

Max Activating Token Index: 566

Text #13

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0458. Min Act: -0.0003

Data Index: 1569476 (Python Code)

Max Activating Token Index: 31

Text #14

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0464. Min Act: -0.0003

Data Index: 396983 (C4 (Web Text))

Max Activating Token Index: 521

Text #15

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0449. Min Act: -0.0003

Data Index: 86890 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0433. Min Act: -0.0003

Data Index: 4356 (C4 (Web Text))

Max Activating Token Index: 291

Text #17

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0446. Min Act: -0.0003

Data Index: 1040185 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0450. Min Act: -0.0003

Data Index: 843796 (C4 (Web Text))

Max Activating Token Index: 651

Text #19

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0442. Min Act: -0.0003

Data Index: 165561 (C4 (Web Text))

Max Activating Token Index: 75