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

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

Neuron 2792 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: 0.0805. Min Range: -0.0805

Max Act: 0.0755. Min Act: -0.0003

Data Index: 320099 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0805. Min Act: -0.0003

Data Index: 993643 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0624. Min Act: -0.0003

Data Index: 567933 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0592. Min Act: -0.0003

Data Index: 475099 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0546. Min Act: -0.0003

Data Index: 603431 (C4 (Web Text))

Max Activating Token Index: 601

Text #5

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0578. Min Act: -0.0003

Data Index: 180233 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0570. Min Act: -0.0003

Data Index: 253562 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0625. Min Act: -0.0003

Data Index: 1062286 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0577. Min Act: -0.0003

Data Index: 343014 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0610. Min Act: -0.0003

Data Index: 101250 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0476. Min Act: -0.0003

Data Index: 562789 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0510. Min Act: -0.0003

Data Index: 934676 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0587. Min Act: -0.0003

Data Index: 442848 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0576. Min Act: -0.0003

Data Index: 129380 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0610. Min Act: -0.0003

Data Index: 714728 (C4 (Web Text))

Max Activating Token Index: 998

Text #15

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0574. Min Act: -0.0003

Data Index: 715936 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0559. Min Act: -0.0003

Data Index: 1637616 (Python Code)

Max Activating Token Index: 629

Text #17

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0542. Min Act: -0.0003

Data Index: 183254 (C4 (Web Text))

Max Activating Token Index: 323

Text #18

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0497. Min Act: -0.0003

Data Index: 1608132 (Python Code)

Max Activating Token Index: 665

Text #19

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0591. Min Act: -0.0003

Data Index: 659532 (C4 (Web Text))

Max Activating Token Index: 219