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

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

Neuron 3992 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: 0.0659. Min Range: -0.0659

Max Act: 0.0657. Min Act: -0.0002

Data Index: 149847 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0659. Min Act: -0.0002

Data Index: 94678 (C4 (Web Text))

Max Activating Token Index: 953

Text #2

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0641. Min Act: -0.0002

Data Index: 8075 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0634. Min Act: -0.0002

Data Index: 1042522 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0633. Min Act: -0.0002

Data Index: 598376 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0602. Min Act: -0.0002

Data Index: 676191 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0599. Min Act: -0.0002

Data Index: 979810 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0608. Min Act: -0.0002

Data Index: 1284622 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0597. Min Act: -0.0002

Data Index: 833600 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0539. Min Act: -0.0002

Data Index: 512578 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0528. Min Act: -0.0002

Data Index: 954361 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0523. Min Act: -0.0002

Data Index: 781809 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0492. Min Act: -0.0002

Data Index: 934886 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0476. Min Act: -0.0002

Data Index: 1153752 (C4 (Web Text))

Max Activating Token Index: 187

Text #14

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0480. Min Act: -0.0002

Data Index: 121429 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0456. Min Act: -0.0002

Data Index: 1327196 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0446. Min Act: -0.0002

Data Index: 752709 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0449. Min Act: -0.0002

Data Index: 1257724 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0422. Min Act: -0.0002

Data Index: 373851 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0418. Min Act: -0.0002

Data Index: 451959 (C4 (Web Text))

Max Activating Token Index: 346