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

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

Neuron 3408 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1690. Min Range: -1.1690

Max Act: 1.1690. Min Act: -0.0000

Data Index: 410515 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 1.1690. Min Range: -1.1690

Max Act: 0.9974. Min Act: -0.0000

Data Index: 321410 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 1.1690. Min Range: -1.1690

Max Act: 1.0286. Min Act: -0.0001

Data Index: 1115333 (C4 (Web Text))

Max Activating Token Index: 485

Text #3

Max Range: 1.1690. Min Range: -1.1690

Max Act: 1.0265. Min Act: -0.0000

Data Index: 503058 (C4 (Web Text))

Max Activating Token Index: 874

Text #4

Max Range: 1.1690. Min Range: -1.1690

Max Act: 0.9417. Min Act: -0.0000

Data Index: 362911 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 1.1690. Min Range: -1.1690

Max Act: 0.9967. Min Act: -0.0001

Data Index: 313026 (C4 (Web Text))

Max Activating Token Index: 606

Text #6

Max Range: 1.1690. Min Range: -1.1690

Max Act: 0.9792. Min Act: -0.0000

Data Index: 428160 (C4 (Web Text))

Max Activating Token Index: 455

Text #7

Max Range: 1.1690. Min Range: -1.1690

Max Act: 0.9398. Min Act: -0.0000

Data Index: 1313862 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 1.1690. Min Range: -1.1690

Max Act: 0.9777. Min Act: -0.0000

Data Index: 307566 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 1.1690. Min Range: -1.1690

Max Act: 0.9284. Min Act: -0.0000

Data Index: 361508 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 1.1690. Min Range: -1.1690

Max Act: 0.8900. Min Act: -0.0001

Data Index: 609984 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 1.1690. Min Range: -1.1690

Max Act: 0.9378. Min Act: -0.0001

Data Index: 734084 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 1.1690. Min Range: -1.1690

Max Act: 0.9004. Min Act: -0.0001

Data Index: 504437 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 1.1690. Min Range: -1.1690

Max Act: 0.8684. Min Act: -0.0001

Data Index: 720702 (C4 (Web Text))

Max Activating Token Index: 122

Text #14

Max Range: 1.1690. Min Range: -1.1690

Max Act: 0.8768. Min Act: -0.0000

Data Index: 1235799 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 1.1690. Min Range: -1.1690

Max Act: 0.8844. Min Act: -0.0000

Data Index: 202598 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 1.1690. Min Range: -1.1690

Max Act: 0.8498. Min Act: -0.0000

Data Index: 1008633 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 1.1690. Min Range: -1.1690

Max Act: 0.8765. Min Act: -0.0000

Data Index: 1195660 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 1.1690. Min Range: -1.1690

Max Act: 0.8168. Min Act: -0.0000

Data Index: 776723 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 1.1690. Min Range: -1.1690

Max Act: 0.8883. Min Act: -0.0000

Data Index: 1144561 (C4 (Web Text))

Max Activating Token Index: 673