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

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

Neuron 877 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: 0.0716. Min Range: -0.0716

Max Act: 0.0716. Min Act: -0.0003

Data Index: 512295 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0594. Min Act: -0.0003

Data Index: 454456 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0568. Min Act: -0.0003

Data Index: 818420 (C4 (Web Text))

Max Activating Token Index: 558

Text #3

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0576. Min Act: -0.0003

Data Index: 866816 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0509. Min Act: -0.0003

Data Index: 1229676 (C4 (Web Text))

Max Activating Token Index: 553

Text #5

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0540. Min Act: -0.0003

Data Index: 1017537 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0423. Min Act: -0.0003

Data Index: 989632 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0440. Min Act: -0.0003

Data Index: 943149 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0465. Min Act: -0.0003

Data Index: 155729 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0473. Min Act: -0.0003

Data Index: 118063 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0532. Min Act: -0.0003

Data Index: 424805 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0488. Min Act: -0.0003

Data Index: 84803 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0497. Min Act: -0.0003

Data Index: 699698 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0513. Min Act: -0.0003

Data Index: 1377137 (Python Code)

Max Activating Token Index: 655

Text #14

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0443. Min Act: -0.0003

Data Index: 736530 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0475. Min Act: -0.0003

Data Index: 1309780 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0477. Min Act: -0.0003

Data Index: 522376 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0479. Min Act: -0.0003

Data Index: 850156 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0434. Min Act: -0.0003

Data Index: 414175 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0476. Min Act: -0.0003

Data Index: 768651 (C4 (Web Text))

Max Activating Token Index: 450