Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2708 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0677. Min Act: -0.0003

Data Index: 217955 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0609. Min Act: -0.0003

Data Index: 29717 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0610. Min Act: -0.0003

Data Index: 1305805 (C4 (Web Text))

Max Activating Token Index: 876

Text #3

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0548. Min Act: -0.0003

Data Index: 459102 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0560. Min Act: -0.0003

Data Index: 806323 (C4 (Web Text))

Max Activating Token Index: 235

Text #5

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0499. Min Act: -0.0003

Data Index: 68684 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0517. Min Act: -0.0003

Data Index: 1135294 (C4 (Web Text))

Max Activating Token Index: 735

Text #7

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0512. Min Act: -0.0003

Data Index: 43252 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0502. Min Act: -0.0004

Data Index: 706568 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0504. Min Act: -0.0003

Data Index: 697437 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0518. Min Act: -0.0003

Data Index: 293663 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0489. Min Act: -0.0003

Data Index: 308292 (C4 (Web Text))

Max Activating Token Index: 937

Text #12

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0488. Min Act: -0.0003

Data Index: 1112486 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0491. Min Act: -0.0003

Data Index: 1065302 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0491. Min Act: -0.0003

Data Index: 5508 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0443. Min Act: -0.0003

Data Index: 426051 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0499. Min Act: -0.0003

Data Index: 589365 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0478. Min Act: -0.0003

Data Index: 769505 (C4 (Web Text))

Max Activating Token Index: 224

Text #18

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0491. Min Act: -0.0003

Data Index: 639086 (C4 (Web Text))

Max Activating Token Index: 960

Text #19

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0466. Min Act: -0.0003

Data Index: 1006696 (C4 (Web Text))

Max Activating Token Index: 859