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

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

Neuron 7 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.5643. Min Act: -0.0000

Data Index: 640060 (C4 (Web Text))

Max Activating Token Index: 370

Text #1

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.4387. Min Act: -0.0000

Data Index: 933717 (C4 (Web Text))

Max Activating Token Index: 57

Text #2

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.4626. Min Act: -0.0000

Data Index: 1000675 (C4 (Web Text))

Max Activating Token Index: 519

Text #3

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.4395. Min Act: -0.0000

Data Index: 60649 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.4130. Min Act: -0.0000

Data Index: 538680 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.4196. Min Act: -0.0000

Data Index: 121193 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.4209. Min Act: -0.0000

Data Index: 868474 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.3861. Min Act: -0.0000

Data Index: 989756 (C4 (Web Text))

Max Activating Token Index: 661

Text #8

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.4056. Min Act: -0.0000

Data Index: 377274 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.4094. Min Act: -0.0000

Data Index: 42535 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.3930. Min Act: -0.0000

Data Index: 1075316 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.3734. Min Act: -0.0000

Data Index: 1416306 (Python Code)

Max Activating Token Index: 43

Text #12

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.3435. Min Act: -0.0000

Data Index: 53522 (C4 (Web Text))

Max Activating Token Index: 358

Text #13

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.3530. Min Act: -0.0000

Data Index: 929073 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.3505. Min Act: -0.0000

Data Index: 1056388 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.3577. Min Act: -0.0000

Data Index: 1203084 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.3590. Min Act: -0.0000

Data Index: 886222 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.3427. Min Act: -0.0000

Data Index: 22699 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.3657. Min Act: -0.0000

Data Index: 76599 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 0.5643. Min Range: -0.5643

Max Act: 0.3550. Min Act: -0.0000

Data Index: 1286815 (C4 (Web Text))

Max Activating Token Index: 73