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

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

Neuron 1674 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.3757. Min Act: -0.0000

Data Index: 1076219 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.3663. Min Act: -0.0000

Data Index: 314921 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.3427. Min Act: -0.0000

Data Index: 1290313 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.3343. Min Act: -0.0000

Data Index: 966751 (C4 (Web Text))

Max Activating Token Index: 649

Text #4

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.3366. Min Act: -0.0000

Data Index: 176615 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2684. Min Act: -0.0000

Data Index: 971972 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2928. Min Act: -0.0000

Data Index: 31506 (C4 (Web Text))

Max Activating Token Index: 538

Text #7

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2887. Min Act: -0.0000

Data Index: 469078 (C4 (Web Text))

Max Activating Token Index: 940

Text #8

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2634. Min Act: -0.0000

Data Index: 1194063 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2894. Min Act: -0.0000

Data Index: 335740 (C4 (Web Text))

Max Activating Token Index: 444

Text #10

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2736. Min Act: -0.0000

Data Index: 294286 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2866. Min Act: -0.0000

Data Index: 642039 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2754. Min Act: -0.0000

Data Index: 1246872 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2413. Min Act: -0.0000

Data Index: 446463 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2613. Min Act: -0.0000

Data Index: 1502160 (Python Code)

Max Activating Token Index: 237

Text #15

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2504. Min Act: -0.0000

Data Index: 1128673 (C4 (Web Text))

Max Activating Token Index: 525

Text #16

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2528. Min Act: -0.0000

Data Index: 1531588 (Python Code)

Max Activating Token Index: 694

Text #17

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2489. Min Act: -0.0000

Data Index: 1211752 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2495. Min Act: -0.0000

Data Index: 1534781 (Python Code)

Max Activating Token Index: 532

Text #19

Max Range: 0.3757. Min Range: -0.3757

Max Act: 0.2630. Min Act: -0.0000

Data Index: 1497517 (Python Code)

Max Activating Token Index: 250