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

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

Neuron 149 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.4534. Min Act: -0.0000

Data Index: 276206 (C4 (Web Text))

Max Activating Token Index: 404

Text #1

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.4235. Min Act: -0.0000

Data Index: 353677 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.4032. Min Act: -0.0000

Data Index: 302141 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.3714. Min Act: -0.0000

Data Index: 49919 (C4 (Web Text))

Max Activating Token Index: 907

Text #4

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.3434. Min Act: -0.0000

Data Index: 91268 (C4 (Web Text))

Max Activating Token Index: 509

Text #5

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.3200. Min Act: -0.0000

Data Index: 304918 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.3044. Min Act: -0.0000

Data Index: 887931 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.3147. Min Act: -0.0000

Data Index: 930646 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.2740. Min Act: -0.0000

Data Index: 698604 (C4 (Web Text))

Max Activating Token Index: 723

Text #9

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.2830. Min Act: -0.0000

Data Index: 924533 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.2760. Min Act: -0.0000

Data Index: 509522 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.2739. Min Act: -0.0000

Data Index: 1437490 (Python Code)

Max Activating Token Index: 662

Text #12

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.2627. Min Act: -0.0000

Data Index: 226497 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.2771. Min Act: -0.0000

Data Index: 1146042 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.2593. Min Act: -0.0000

Data Index: 1319725 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.2625. Min Act: -0.0000

Data Index: 969089 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.2558. Min Act: -0.0000

Data Index: 1008661 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.2561. Min Act: -0.0000

Data Index: 813406 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.2465. Min Act: -0.0000

Data Index: 765474 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.2525. Min Act: -0.0000

Data Index: 504949 (C4 (Web Text))

Max Activating Token Index: 268