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

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

Neuron 4061 in Layer 0

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: 0.0684. Min Range: -0.0684

Max Act: 0.0677. Min Act: -0.0001

Data Index: 1016336 (C4 (Web Text))

Max Activating Token Index: 497

Text #1

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0684. Min Act: -0.0001

Data Index: 296256 (C4 (Web Text))

Max Activating Token Index: 284

Text #2

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0660. Min Act: -0.0001

Data Index: 18634 (C4 (Web Text))

Max Activating Token Index: 508

Text #3

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0647. Min Act: -0.0001

Data Index: 747095 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0649. Min Act: -0.0001

Data Index: 1109800 (C4 (Web Text))

Max Activating Token Index: 517

Text #5

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0646. Min Act: -0.0001

Data Index: 543785 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0639. Min Act: -0.0001

Data Index: 616302 (C4 (Web Text))

Max Activating Token Index: 780

Text #7

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0620. Min Act: -0.0001

Data Index: 585380 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0632. Min Act: -0.0001

Data Index: 822241 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0641. Min Act: -0.0001

Data Index: 603901 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0619. Min Act: -0.0001

Data Index: 1088183 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0629. Min Act: -0.0001

Data Index: 1328196 (C4 (Web Text))

Max Activating Token Index: 398

Text #12

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0609. Min Act: -0.0001

Data Index: 113110 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0601. Min Act: -0.0001

Data Index: 260843 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0614. Min Act: -0.0001

Data Index: 302213 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0609. Min Act: -0.0001

Data Index: 1126462 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0603. Min Act: -0.0001

Data Index: 932547 (C4 (Web Text))

Max Activating Token Index: 267

Text #17

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0611. Min Act: -0.0001

Data Index: 390214 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0603. Min Act: -0.0001

Data Index: 889379 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0604. Min Act: -0.0001

Data Index: 613316 (C4 (Web Text))

Max Activating Token Index: 945