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

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

Neuron 3004 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: 0.0664. Min Range: -0.0664

Max Act: 0.0664. Min Act: -0.0003

Data Index: 839689 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0655. Min Act: -0.0003

Data Index: 472602 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0629. Min Act: -0.0003

Data Index: 814905 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0615. Min Act: -0.0003

Data Index: 756674 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0616. Min Act: -0.0003

Data Index: 901719 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0596. Min Act: -0.0003

Data Index: 259498 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0615. Min Act: -0.0003

Data Index: 629893 (C4 (Web Text))

Max Activating Token Index: 143

Text #7

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0540. Min Act: -0.0003

Data Index: 33659 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0531. Min Act: -0.0003

Data Index: 1105372 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0552. Min Act: -0.0003

Data Index: 1340654 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0514. Min Act: -0.0003

Data Index: 1196427 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0506. Min Act: -0.0003

Data Index: 962902 (C4 (Web Text))

Max Activating Token Index: 429

Text #12

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0502. Min Act: -0.0003

Data Index: 873370 (C4 (Web Text))

Max Activating Token Index: 844

Text #13

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0494. Min Act: -0.0003

Data Index: 455761 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0496. Min Act: -0.0003

Data Index: 1328766 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0503. Min Act: -0.0003

Data Index: 479206 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0481. Min Act: -0.0003

Data Index: 19104 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0480. Min Act: -0.0003

Data Index: 1320578 (C4 (Web Text))

Max Activating Token Index: 847

Text #18

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0462. Min Act: -0.0003

Data Index: 847478 (C4 (Web Text))

Max Activating Token Index: 272

Text #19

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0474. Min Act: -0.0003

Data Index: 944495 (C4 (Web Text))

Max Activating Token Index: 508