Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4375 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0720. Min Act: -0.0000

Data Index: 986430 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0648. Min Act: -0.0001

Data Index: 1013127 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0661. Min Act: -0.0000

Data Index: 872403 (C4 (Web Text))

Max Activating Token Index: 998

Text #3

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0598. Min Act: -0.0000

Data Index: 844828 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0559. Min Act: -0.0000

Data Index: 1013000 (C4 (Web Text))

Max Activating Token Index: 985

Text #5

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0572. Min Act: -0.0000

Data Index: 418503 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0555. Min Act: -0.0000

Data Index: 1132834 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0561. Min Act: -0.0001

Data Index: 1216637 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0532. Min Act: -0.0001

Data Index: 186260 (C4 (Web Text))

Max Activating Token Index: 311

Text #9

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0504. Min Act: -0.0001

Data Index: 397359 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0539. Min Act: -0.0001

Data Index: 914125 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0581. Min Act: -0.0000

Data Index: 944996 (C4 (Web Text))

Max Activating Token Index: 847

Text #12

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0528. Min Act: -0.0001

Data Index: 1204610 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0528. Min Act: -0.0000

Data Index: 104179 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0526. Min Act: -0.0000

Data Index: 968899 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0515. Min Act: -0.0001

Data Index: 552441 (C4 (Web Text))

Max Activating Token Index: 300

Text #16

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0524. Min Act: -0.0000

Data Index: 670615 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0522. Min Act: -0.0001

Data Index: 591226 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0521. Min Act: -0.0000

Data Index: 969577 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0534. Min Act: -0.0000

Data Index: 5567 (C4 (Web Text))

Max Activating Token Index: 811