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

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

Neuron 2096 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: 0.4455. Min Range: -0.4455

Max Act: 0.4455. Min Act: -0.0002

Data Index: 527414 (C4 (Web Text))

Max Activating Token Index: 532

Text #1

Max Range: 0.4455. Min Range: -0.4455

Max Act: 0.4427. Min Act: -0.0002

Data Index: 379945 (C4 (Web Text))

Max Activating Token Index: 799

Text #2

Max Range: 0.4455. Min Range: -0.4455

Max Act: 0.3880. Min Act: -0.0002

Data Index: 762703 (C4 (Web Text))

Max Activating Token Index: 311

Text #3

Max Range: 0.4455. Min Range: -0.4455

Max Act: 0.3813. Min Act: -0.0002

Data Index: 40153 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 0.4455. Min Range: -0.4455

Max Act: 0.3808. Min Act: -0.0002

Data Index: 818757 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 0.4455. Min Range: -0.4455

Max Act: 0.3421. Min Act: -0.0002

Data Index: 671763 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 0.4455. Min Range: -0.4455

Max Act: 0.3925. Min Act: -0.0002

Data Index: 887567 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 0.4455. Min Range: -0.4455

Max Act: 0.3897. Min Act: -0.0002

Data Index: 862206 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 0.4455. Min Range: -0.4455

Max Act: 0.3873. Min Act: -0.0002

Data Index: 1136172 (C4 (Web Text))

Max Activating Token Index: 317

Text #9

Max Range: 0.4455. Min Range: -0.4455

Max Act: 0.3746. Min Act: -0.0002

Data Index: 1119249 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 0.4455. Min Range: -0.4455

Max Act: 0.3819. Min Act: -0.0002

Data Index: 376344 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 0.4455. Min Range: -0.4455

Max Act: 0.3461. Min Act: -0.0002

Data Index: 658011 (C4 (Web Text))

Max Activating Token Index: 493

Text #12

Max Range: 0.4455. Min Range: -0.4455

Max Act: 0.3568. Min Act: -0.0002

Data Index: 526622 (C4 (Web Text))

Max Activating Token Index: 940

Text #13

Max Range: 0.4455. Min Range: -0.4455

Max Act: 0.3537. Min Act: -0.0002

Data Index: 616703 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 0.4455. Min Range: -0.4455

Max Act: 0.3385. Min Act: -0.0002

Data Index: 659526 (C4 (Web Text))

Max Activating Token Index: 868

Text #15

Max Range: 0.4455. Min Range: -0.4455

Max Act: 0.3392. Min Act: -0.0002

Data Index: 1207775 (C4 (Web Text))

Max Activating Token Index: 449

Text #16

Max Range: 0.4455. Min Range: -0.4455

Max Act: 0.3620. Min Act: -0.0002

Data Index: 915739 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 0.4455. Min Range: -0.4455

Max Act: 0.3727. Min Act: -0.0002

Data Index: 344253 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 0.4455. Min Range: -0.4455

Max Act: 0.3590. Min Act: -0.0002

Data Index: 868392 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 0.4455. Min Range: -0.4455

Max Act: 0.3340. Min Act: -0.0002

Data Index: 667929 (C4 (Web Text))

Max Activating Token Index: 55