Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1664 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0555. Min Act: -0.0003

Data Index: 656714 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0560. Min Act: -0.0003

Data Index: 833323 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0538. Min Act: -0.0003

Data Index: 58089 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0544. Min Act: -0.0004

Data Index: 892082 (C4 (Web Text))

Max Activating Token Index: 598

Text #4

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0531. Min Act: -0.0003

Data Index: 483059 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0550. Min Act: -0.0004

Data Index: 588624 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0538. Min Act: -0.0003

Data Index: 699782 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0548. Min Act: -0.0003

Data Index: 1023058 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0538. Min Act: -0.0003

Data Index: 1087076 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0534. Min Act: -0.0004

Data Index: 1287180 (C4 (Web Text))

Max Activating Token Index: 768

Text #10

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0534. Min Act: -0.0003

Data Index: 636749 (C4 (Web Text))

Max Activating Token Index: 622

Text #11

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0540. Min Act: -0.0004

Data Index: 378863 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0540. Min Act: -0.0003

Data Index: 1108992 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0518. Min Act: -0.0004

Data Index: 1254006 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0513. Min Act: -0.0003

Data Index: 1172747 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0518. Min Act: -0.0004

Data Index: 100777 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0525. Min Act: -0.0004

Data Index: 990700 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0496. Min Act: -0.0003

Data Index: 788074 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0511. Min Act: -0.0004

Data Index: 322835 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0515. Min Act: -0.0003

Data Index: 790003 (C4 (Web Text))

Max Activating Token Index: 160