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

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

Neuron 3365 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.8057. Min Act: -0.0000

Data Index: 777785 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.5805. Min Act: -0.0000

Data Index: 228933 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.5400. Min Act: -0.0000

Data Index: 1250522 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.5488. Min Act: -0.0000

Data Index: 801333 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.4941. Min Act: -0.0000

Data Index: 435618 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.5216. Min Act: -0.0000

Data Index: 695418 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.5106. Min Act: -0.0000

Data Index: 705941 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.4669. Min Act: -0.0000

Data Index: 832606 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.4731. Min Act: -0.0000

Data Index: 692330 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.5138. Min Act: -0.0000

Data Index: 1068760 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.4525. Min Act: -0.0000

Data Index: 1216394 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.4613. Min Act: -0.0000

Data Index: 1056993 (C4 (Web Text))

Max Activating Token Index: 511

Text #12

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.4454. Min Act: -0.0000

Data Index: 1124412 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.4279. Min Act: -0.0000

Data Index: 816522 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.4233. Min Act: -0.0000

Data Index: 642880 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.4552. Min Act: -0.0000

Data Index: 910435 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.4477. Min Act: -0.0000

Data Index: 480411 (C4 (Web Text))

Max Activating Token Index: 920

Text #17

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.4339. Min Act: -0.0000

Data Index: 299618 (C4 (Web Text))

Max Activating Token Index: 721

Text #18

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.4462. Min Act: -0.0000

Data Index: 1205776 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 0.8057. Min Range: -0.8057

Max Act: 0.4536. Min Act: -0.0000

Data Index: 1321083 (C4 (Web Text))

Max Activating Token Index: 246