Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 286 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0595. Min Act: -0.0003

Data Index: 729678 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0538. Min Act: -0.0003

Data Index: 483683 (C4 (Web Text))

Max Activating Token Index: 903

Text #2

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0535. Min Act: -0.0003

Data Index: 411792 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0518. Min Act: -0.0002

Data Index: 1534702 (Python Code)

Max Activating Token Index: 131

Text #4

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0533. Min Act: -0.0003

Data Index: 1242346 (C4 (Web Text))

Max Activating Token Index: 694

Text #5

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0522. Min Act: -0.0003

Data Index: 1242129 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0511. Min Act: -0.0004

Data Index: 848255 (C4 (Web Text))

Max Activating Token Index: 383

Text #7

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0519. Min Act: -0.0003

Data Index: 245243 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0514. Min Act: -0.0002

Data Index: 350364 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0493. Min Act: -0.0003

Data Index: 184450 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0512. Min Act: -0.0003

Data Index: 275876 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0506. Min Act: -0.0002

Data Index: 1335218 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0495. Min Act: -0.0003

Data Index: 1043910 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0498. Min Act: -0.0002

Data Index: 728093 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0497. Min Act: -0.0003

Data Index: 583068 (C4 (Web Text))

Max Activating Token Index: 865

Text #15

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0477. Min Act: -0.0003

Data Index: 844769 (C4 (Web Text))

Max Activating Token Index: 454

Text #16

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0474. Min Act: -0.0002

Data Index: 326780 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0479. Min Act: -0.0003

Data Index: 541440 (C4 (Web Text))

Max Activating Token Index: 936

Text #18

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0482. Min Act: -0.0003

Data Index: 925701 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0478. Min Act: -0.0003

Data Index: 676867 (C4 (Web Text))

Max Activating Token Index: 334