Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 912 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0623. Min Act: -0.0003

Data Index: 1322410 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0550. Min Act: -0.0003

Data Index: 219899 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0556. Min Act: -0.0003

Data Index: 1499361 (Python Code)

Max Activating Token Index: 512

Text #3

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0549. Min Act: -0.0003

Data Index: 1042251 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0536. Min Act: -0.0003

Data Index: 76584 (C4 (Web Text))

Max Activating Token Index: 365

Text #5

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0523. Min Act: -0.0003

Data Index: 1111760 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0531. Min Act: -0.0003

Data Index: 68869 (C4 (Web Text))

Max Activating Token Index: 640

Text #7

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0510. Min Act: -0.0003

Data Index: 1535832 (Python Code)

Max Activating Token Index: 323

Text #8

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0504. Min Act: -0.0003

Data Index: 1438849 (Python Code)

Max Activating Token Index: 645

Text #9

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0513. Min Act: -0.0003

Data Index: 1250206 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0496. Min Act: -0.0003

Data Index: 1433263 (Python Code)

Max Activating Token Index: 395

Text #11

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0491. Min Act: -0.0004

Data Index: 169453 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0487. Min Act: -0.0003

Data Index: 1190025 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0481. Min Act: -0.0003

Data Index: 809343 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0470. Min Act: -0.0003

Data Index: 1011322 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0473. Min Act: -0.0003

Data Index: 617235 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0473. Min Act: -0.0003

Data Index: 665654 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0469. Min Act: -0.0003

Data Index: 1277261 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0464. Min Act: -0.0003

Data Index: 396097 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0458. Min Act: -0.0003

Data Index: 1427318 (Python Code)

Max Activating Token Index: 73