Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2757 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.8569. Min Act: -0.0000

Data Index: 1439903 (Python Code)

Max Activating Token Index: 638

Text #1

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.8102. Min Act: -0.0000

Data Index: 1625253 (Python Code)

Max Activating Token Index: 303

Text #2

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.7147. Min Act: -0.0000

Data Index: 899659 (C4 (Web Text))

Max Activating Token Index: 850

Text #3

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.6735. Min Act: -0.0000

Data Index: 1068644 (C4 (Web Text))

Max Activating Token Index: 598

Text #4

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.6433. Min Act: -0.0001

Data Index: 812532 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.5978. Min Act: -0.0000

Data Index: 1012879 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.5590. Min Act: -0.0000

Data Index: 917725 (C4 (Web Text))

Max Activating Token Index: 823

Text #7

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.6620. Min Act: -0.0000

Data Index: 690442 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.6671. Min Act: -0.0000

Data Index: 622128 (C4 (Web Text))

Max Activating Token Index: 293

Text #9

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.5826. Min Act: -0.0000

Data Index: 1213078 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.6990. Min Act: -0.0000

Data Index: 1044190 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.5831. Min Act: -0.0000

Data Index: 690771 (C4 (Web Text))

Max Activating Token Index: 545

Text #12

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.5560. Min Act: -0.0000

Data Index: 549354 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.5761. Min Act: -0.0000

Data Index: 1620215 (Python Code)

Max Activating Token Index: 808

Text #14

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.5036. Min Act: -0.0000

Data Index: 173347 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.5672. Min Act: -0.0000

Data Index: 1460893 (Python Code)

Max Activating Token Index: 432

Text #16

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.5535. Min Act: -0.0000

Data Index: 162768 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.5199. Min Act: -0.0000

Data Index: 1357367 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.4839. Min Act: -0.0000

Data Index: 1621199 (Python Code)

Max Activating Token Index: 107

Text #19

Max Range: 0.8569. Min Range: -0.8569

Max Act: 0.5034. Min Act: -0.0000

Data Index: 1414971 (Python Code)

Max Activating Token Index: 632