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

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

Neuron 4903 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0688. Min Act: -0.0000

Data Index: 253602 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0615. Min Act: -0.0000

Data Index: 1350333 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0680. Min Act: -0.0000

Data Index: 554090 (C4 (Web Text))

Max Activating Token Index: 384

Text #3

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0625. Min Act: -0.0000

Data Index: 881820 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0632. Min Act: -0.0000

Data Index: 166186 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0604. Min Act: -0.0000

Data Index: 368131 (C4 (Web Text))

Max Activating Token Index: 569

Text #6

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0555. Min Act: -0.0000

Data Index: 202237 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0591. Min Act: -0.0000

Data Index: 488273 (C4 (Web Text))

Max Activating Token Index: 65

Text #8

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0576. Min Act: -0.0000

Data Index: 1063193 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0493. Min Act: -0.0000

Data Index: 493115 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0518. Min Act: -0.0000

Data Index: 1178795 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0553. Min Act: -0.0000

Data Index: 1094433 (C4 (Web Text))

Max Activating Token Index: 944

Text #12

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0478. Min Act: -0.0000

Data Index: 1406898 (Python Code)

Max Activating Token Index: 69

Text #13

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0479. Min Act: -0.0000

Data Index: 195540 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0454. Min Act: -0.0000

Data Index: 245482 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0437. Min Act: -0.0000

Data Index: 873804 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0401. Min Act: -0.0000

Data Index: 855179 (C4 (Web Text))

Max Activating Token Index: 369

Text #17

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0464. Min Act: -0.0000

Data Index: 1056295 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0462. Min Act: -0.0000

Data Index: 728480 (C4 (Web Text))

Max Activating Token Index: 686

Text #19

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0445. Min Act: -0.0000

Data Index: 540069 (C4 (Web Text))

Max Activating Token Index: 110