Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2015 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0546. Min Act: -0.0003

Data Index: 1215513 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0487. Min Act: -0.0003

Data Index: 1186617 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0498. Min Act: -0.0003

Data Index: 196374 (C4 (Web Text))

Max Activating Token Index: 577

Text #3

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0444. Min Act: -0.0003

Data Index: 1038369 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0479. Min Act: -0.0003

Data Index: 1351035 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0453. Min Act: -0.0003

Data Index: 161484 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0459. Min Act: -0.0003

Data Index: 448026 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0455. Min Act: -0.0003

Data Index: 398292 (C4 (Web Text))

Max Activating Token Index: 531

Text #8

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0456. Min Act: -0.0003

Data Index: 456180 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0468. Min Act: -0.0003

Data Index: 844740 (C4 (Web Text))

Max Activating Token Index: 1003

Text #10

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0417. Min Act: -0.0003

Data Index: 1342495 (C4 (Web Text))

Max Activating Token Index: 878

Text #11

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0392. Min Act: -0.0003

Data Index: 648457 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0416. Min Act: -0.0003

Data Index: 188397 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0424. Min Act: -0.0003

Data Index: 290022 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0431. Min Act: -0.0003

Data Index: 1240017 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0380. Min Act: -0.0003

Data Index: 446678 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0417. Min Act: -0.0003

Data Index: 330030 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0426. Min Act: -0.0003

Data Index: 195729 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0398. Min Act: -0.0003

Data Index: 1273557 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0394. Min Act: -0.0003

Data Index: 20372 (C4 (Web Text))

Max Activating Token Index: 846