Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3804 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9389. Min Range: -1.9389

Max Act: 1.9389. Min Act: -0.0001

Data Index: 917416 (C4 (Web Text))

Max Activating Token Index: 635

Text #1

Max Range: 1.9389. Min Range: -1.9389

Max Act: 1.8850. Min Act: -0.0001

Data Index: 429858 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 1.9389. Min Range: -1.9389

Max Act: 1.8026. Min Act: -0.0001

Data Index: 1399222 (Python Code)

Max Activating Token Index: 228

Text #3

Max Range: 1.9389. Min Range: -1.9389

Max Act: 1.8447. Min Act: -0.0001

Data Index: 1200927 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 1.9389. Min Range: -1.9389

Max Act: 1.4413. Min Act: -0.0001

Data Index: 1481172 (Python Code)

Max Activating Token Index: 308

Text #5

Max Range: 1.9389. Min Range: -1.9389

Max Act: 1.5782. Min Act: -0.0001

Data Index: 205650 (C4 (Web Text))

Max Activating Token Index: 405

Text #6

Max Range: 1.9389. Min Range: -1.9389

Max Act: 1.6430. Min Act: -0.0001

Data Index: 656499 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 1.9389. Min Range: -1.9389

Max Act: 1.5339. Min Act: -0.0001

Data Index: 393012 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 1.9389. Min Range: -1.9389

Max Act: 1.4122. Min Act: -0.0001

Data Index: 771974 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 1.9389. Min Range: -1.9389

Max Act: 1.2786. Min Act: -0.0001

Data Index: 1132073 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 1.9389. Min Range: -1.9389

Max Act: 1.3889. Min Act: -0.0001

Data Index: 662284 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 1.9389. Min Range: -1.9389

Max Act: 1.3338. Min Act: -0.0001

Data Index: 1457680 (Python Code)

Max Activating Token Index: 716

Text #12

Max Range: 1.9389. Min Range: -1.9389

Max Act: 1.5230. Min Act: -0.0001

Data Index: 883465 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 1.9389. Min Range: -1.9389

Max Act: 1.3856. Min Act: -0.0001

Data Index: 5868 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 1.9389. Min Range: -1.9389

Max Act: 1.2545. Min Act: -0.0001

Data Index: 1540558 (Python Code)

Max Activating Token Index: 381

Text #15

Max Range: 1.9389. Min Range: -1.9389

Max Act: 1.3860. Min Act: -0.0001

Data Index: 77193 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 1.9389. Min Range: -1.9389

Max Act: 1.3525. Min Act: -0.0001

Data Index: 679351 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 1.9389. Min Range: -1.9389

Max Act: 1.5849. Min Act: -0.0001

Data Index: 256186 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 1.9389. Min Range: -1.9389

Max Act: 1.5650. Min Act: -0.0001

Data Index: 322317 (C4 (Web Text))

Max Activating Token Index: 392

Text #19

Max Range: 1.9389. Min Range: -1.9389

Max Act: 1.4305. Min Act: -0.0001

Data Index: 959020 (C4 (Web Text))

Max Activating Token Index: 348