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

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

Neuron 1698 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4167. Min Range: -0.4167

Max Act: 0.4088. Min Act: -0.0000

Data Index: 998889 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 0.4167. Min Range: -0.4167

Max Act: 0.4167. Min Act: -0.0000

Data Index: 753898 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 0.4167. Min Range: -0.4167

Max Act: 0.3782. Min Act: 0.0000

Data Index: 584000 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 0.4167. Min Range: -0.4167

Max Act: 0.3442. Min Act: -0.0000

Data Index: 374606 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 0.4167. Min Range: -0.4167

Max Act: 0.3397. Min Act: -0.0000

Data Index: 362750 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 0.4167. Min Range: -0.4167

Max Act: 0.3278. Min Act: -0.0000

Data Index: 965314 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 0.4167. Min Range: -0.4167

Max Act: 0.3217. Min Act: -0.0000

Data Index: 1007929 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 0.4167. Min Range: -0.4167

Max Act: 0.3202. Min Act: -0.0000

Data Index: 792043 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 0.4167. Min Range: -0.4167

Max Act: 0.3088. Min Act: -0.0000

Data Index: 752157 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 0.4167. Min Range: -0.4167

Max Act: 0.2920. Min Act: -0.0000

Data Index: 715124 (C4 (Web Text))

Max Activating Token Index: 561

Text #10

Max Range: 0.4167. Min Range: -0.4167

Max Act: 0.2768. Min Act: -0.0000

Data Index: 1001030 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 0.4167. Min Range: -0.4167

Max Act: 0.2707. Min Act: -0.0000

Data Index: 360168 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 0.4167. Min Range: -0.4167

Max Act: 0.2914. Min Act: -0.0000

Data Index: 1280307 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 0.4167. Min Range: -0.4167

Max Act: 0.2951. Min Act: -0.0000

Data Index: 165914 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 0.4167. Min Range: -0.4167

Max Act: 0.2904. Min Act: -0.0000

Data Index: 734485 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 0.4167. Min Range: -0.4167

Max Act: 0.2711. Min Act: -0.0000

Data Index: 1068048 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 0.4167. Min Range: -0.4167

Max Act: 0.2666. Min Act: -0.0000

Data Index: 1158493 (C4 (Web Text))

Max Activating Token Index: 669

Text #17

Max Range: 0.4167. Min Range: -0.4167

Max Act: 0.2741. Min Act: -0.0000

Data Index: 1332504 (C4 (Web Text))

Max Activating Token Index: 799

Text #18

Max Range: 0.4167. Min Range: -0.4167

Max Act: 0.2702. Min Act: -0.0000

Data Index: 246528 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 0.4167. Min Range: -0.4167

Max Act: 0.2571. Min Act: -0.0000

Data Index: 1093784 (C4 (Web Text))

Max Activating Token Index: 101