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

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

Neuron 1440 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: 0.7577. Min Range: -0.7577

Max Act: 0.7577. Min Act: -0.0000

Data Index: 1236565 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 0.7577. Min Range: -0.7577

Max Act: 0.7105. Min Act: -0.0000

Data Index: 1039531 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 0.7577. Min Range: -0.7577

Max Act: 0.6696. Min Act: 0.0000

Data Index: 1536813 (Python Code)

Max Activating Token Index: 473

Text #3

Max Range: 0.7577. Min Range: -0.7577

Max Act: 0.5753. Min Act: -0.0000

Data Index: 69651 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 0.7577. Min Range: -0.7577

Max Act: 0.5576. Min Act: 0.0000

Data Index: 1364565 (Python Code)

Max Activating Token Index: 621

Text #5

Max Range: 0.7577. Min Range: -0.7577

Max Act: 0.5106. Min Act: -0.0000

Data Index: 1144296 (C4 (Web Text))

Max Activating Token Index: 525

Text #6

Max Range: 0.7577. Min Range: -0.7577

Max Act: 0.5015. Min Act: -0.0000

Data Index: 1616729 (Python Code)

Max Activating Token Index: 1011

Text #7

Max Range: 0.7577. Min Range: -0.7577

Max Act: 0.4734. Min Act: -0.0000

Data Index: 1191356 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 0.7577. Min Range: -0.7577

Max Act: 0.4766. Min Act: -0.0000

Data Index: 921506 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 0.7577. Min Range: -0.7577

Max Act: 0.4776. Min Act: -0.0000

Data Index: 830365 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 0.7577. Min Range: -0.7577

Max Act: 0.5088. Min Act: -0.0000

Data Index: 1040309 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 0.7577. Min Range: -0.7577

Max Act: 0.4792. Min Act: -0.0000

Data Index: 738647 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 0.7577. Min Range: -0.7577

Max Act: 0.4723. Min Act: -0.0000

Data Index: 1287304 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 0.7577. Min Range: -0.7577

Max Act: 0.5015. Min Act: -0.0000

Data Index: 1273134 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 0.7577. Min Range: -0.7577

Max Act: 0.4510. Min Act: -0.0000

Data Index: 622029 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 0.7577. Min Range: -0.7577

Max Act: 0.4373. Min Act: -0.0000

Data Index: 1148011 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 0.7577. Min Range: -0.7577

Max Act: 0.4625. Min Act: -0.0000

Data Index: 989575 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 0.7577. Min Range: -0.7577

Max Act: 0.4632. Min Act: -0.0000

Data Index: 1431769 (Python Code)

Max Activating Token Index: 707

Text #18

Max Range: 0.7577. Min Range: -0.7577

Max Act: 0.4540. Min Act: -0.0000

Data Index: 1615353 (Python Code)

Max Activating Token Index: 90

Text #19

Max Range: 0.7577. Min Range: -0.7577

Max Act: 0.4549. Min Act: -0.0000

Data Index: 378817 (C4 (Web Text))

Max Activating Token Index: 509