Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 838 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6607. Min Range: -0.6607

Max Act: 0.6505. Min Act: -0.0001

Data Index: 1078615 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 0.6607. Min Range: -0.6607

Max Act: 0.6607. Min Act: -0.0001

Data Index: 333312 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 0.6607. Min Range: -0.6607

Max Act: 0.5696. Min Act: -0.0001

Data Index: 348212 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 0.6607. Min Range: -0.6607

Max Act: 0.6054. Min Act: -0.0000

Data Index: 878187 (C4 (Web Text))

Max Activating Token Index: 996

Text #4

Max Range: 0.6607. Min Range: -0.6607

Max Act: 0.5484. Min Act: -0.0000

Data Index: 799351 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 0.6607. Min Range: -0.6607

Max Act: 0.6139. Min Act: -0.0001

Data Index: 956933 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 0.6607. Min Range: -0.6607

Max Act: 0.5378. Min Act: -0.0001

Data Index: 821287 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 0.6607. Min Range: -0.6607

Max Act: 0.5715. Min Act: -0.0000

Data Index: 811412 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 0.6607. Min Range: -0.6607

Max Act: 0.5520. Min Act: -0.0000

Data Index: 670226 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 0.6607. Min Range: -0.6607

Max Act: 0.5795. Min Act: -0.0000

Data Index: 955175 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 0.6607. Min Range: -0.6607

Max Act: 0.5486. Min Act: -0.0000

Data Index: 868686 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 0.6607. Min Range: -0.6607

Max Act: 0.5474. Min Act: -0.0000

Data Index: 1057181 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 0.6607. Min Range: -0.6607

Max Act: 0.5450. Min Act: -0.0001

Data Index: 951136 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 0.6607. Min Range: -0.6607

Max Act: 0.4645. Min Act: -0.0001

Data Index: 331998 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 0.6607. Min Range: -0.6607

Max Act: 0.5182. Min Act: -0.0000

Data Index: 1098201 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 0.6607. Min Range: -0.6607

Max Act: 0.5110. Min Act: -0.0000

Data Index: 371700 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 0.6607. Min Range: -0.6607

Max Act: 0.5429. Min Act: -0.0001

Data Index: 729616 (C4 (Web Text))

Max Activating Token Index: 850

Text #17

Max Range: 0.6607. Min Range: -0.6607

Max Act: 0.4863. Min Act: -0.0000

Data Index: 1026815 (C4 (Web Text))

Max Activating Token Index: 6

Text #18

Max Range: 0.6607. Min Range: -0.6607

Max Act: 0.5280. Min Act: -0.0000

Data Index: 1100784 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 0.6607. Min Range: -0.6607

Max Act: 0.5011. Min Act: -0.0001

Data Index: 45825 (C4 (Web Text))

Max Activating Token Index: 904