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

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

Neuron 2727 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0704. Min Act: -0.0002

Data Index: 1490483 (Python Code)

Max Activating Token Index: 14

Text #1

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0589. Min Act: -0.0002

Data Index: 1597705 (Python Code)

Max Activating Token Index: 631

Text #2

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0571. Min Act: -0.0002

Data Index: 933883 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0571. Min Act: -0.0002

Data Index: 384591 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0529. Min Act: -0.0002

Data Index: 1636478 (Python Code)

Max Activating Token Index: 864

Text #5

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0525. Min Act: -0.0002

Data Index: 80834 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0500. Min Act: -0.0002

Data Index: 49536 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0492. Min Act: -0.0002

Data Index: 1375264 (Python Code)

Max Activating Token Index: 892

Text #8

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0485. Min Act: -0.0002

Data Index: 1356702 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0487. Min Act: -0.0002

Data Index: 1639600 (Python Code)

Max Activating Token Index: 137

Text #10

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0476. Min Act: -0.0002

Data Index: 1505542 (Python Code)

Max Activating Token Index: 892

Text #11

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1122628 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0472. Min Act: -0.0002

Data Index: 1443680 (Python Code)

Max Activating Token Index: 748

Text #13

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0448. Min Act: -0.0002

Data Index: 1511635 (Python Code)

Max Activating Token Index: 791

Text #14

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1647672 (Python Code)

Max Activating Token Index: 171

Text #15

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0462. Min Act: -0.0002

Data Index: 1607007 (Python Code)

Max Activating Token Index: 751

Text #16

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0442. Min Act: -0.0002

Data Index: 1499331 (Python Code)

Max Activating Token Index: 647

Text #17

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0446. Min Act: -0.0002

Data Index: 1383233 (Python Code)

Max Activating Token Index: 843

Text #18

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0444. Min Act: -0.0002

Data Index: 1534634 (Python Code)

Max Activating Token Index: 996

Text #19

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0446. Min Act: -0.0002

Data Index: 1365815 (Python Code)

Max Activating Token Index: 769