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

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

Neuron 4451 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1885. Min Range: -2.1885

Max Act: 2.1885. Min Act: -0.0000

Data Index: 131726 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 2.1885. Min Range: -2.1885

Max Act: 2.0478. Min Act: -0.0000

Data Index: 52663 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 2.1885. Min Range: -2.1885

Max Act: 1.8427. Min Act: -0.0001

Data Index: 64198 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 2.1885. Min Range: -2.1885

Max Act: 1.9333. Min Act: -0.0000

Data Index: 1286999 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 2.1885. Min Range: -2.1885

Max Act: 1.8808. Min Act: -0.0000

Data Index: 902433 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 2.1885. Min Range: -2.1885

Max Act: 2.1531. Min Act: -0.0000

Data Index: 355726 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 2.1885. Min Range: -2.1885

Max Act: 2.0324. Min Act: -0.0000

Data Index: 631001 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 2.1885. Min Range: -2.1885

Max Act: 1.8137. Min Act: -0.0000

Data Index: 310774 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 2.1885. Min Range: -2.1885

Max Act: 1.7718. Min Act: -0.0000

Data Index: 610775 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 2.1885. Min Range: -2.1885

Max Act: 1.5738. Min Act: -0.0000

Data Index: 355155 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 2.1885. Min Range: -2.1885

Max Act: 1.8050. Min Act: -0.0000

Data Index: 855060 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 2.1885. Min Range: -2.1885

Max Act: 1.7090. Min Act: -0.0000

Data Index: 1140977 (C4 (Web Text))

Max Activating Token Index: 426

Text #12

Max Range: 2.1885. Min Range: -2.1885

Max Act: 1.5874. Min Act: -0.0000

Data Index: 65772 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 2.1885. Min Range: -2.1885

Max Act: 1.5922. Min Act: -0.0000

Data Index: 83288 (C4 (Web Text))

Max Activating Token Index: 909

Text #14

Max Range: 2.1885. Min Range: -2.1885

Max Act: 1.5496. Min Act: -0.0001

Data Index: 591463 (C4 (Web Text))

Max Activating Token Index: 494

Text #15

Max Range: 2.1885. Min Range: -2.1885

Max Act: 1.6181. Min Act: -0.0000

Data Index: 304688 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 2.1885. Min Range: -2.1885

Max Act: 1.7051. Min Act: -0.0000

Data Index: 1155611 (C4 (Web Text))

Max Activating Token Index: 207

Text #17

Max Range: 2.1885. Min Range: -2.1885

Max Act: 1.5294. Min Act: -0.0000

Data Index: 845709 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 2.1885. Min Range: -2.1885

Max Act: 1.5200. Min Act: -0.0000

Data Index: 849082 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 2.1885. Min Range: -2.1885

Max Act: 1.5109. Min Act: -0.0000

Data Index: 1343503 (C4 (Web Text))

Max Activating Token Index: 199