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

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

Neuron 837 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0563. Min Range: -2.0563

Max Act: 2.0563. Min Act: -0.0000

Data Index: 446842 (C4 (Web Text))

Max Activating Token Index: 666

Text #1

Max Range: 2.0563. Min Range: -2.0563

Max Act: 1.9976. Min Act: -0.0000

Data Index: 138933 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 2.0563. Min Range: -2.0563

Max Act: 1.8490. Min Act: -0.0000

Data Index: 1312213 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 2.0563. Min Range: -2.0563

Max Act: 1.7608. Min Act: -0.0000

Data Index: 22197 (C4 (Web Text))

Max Activating Token Index: 821

Text #4

Max Range: 2.0563. Min Range: -2.0563

Max Act: 1.9092. Min Act: -0.0000

Data Index: 497429 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 2.0563. Min Range: -2.0563

Max Act: 1.8004. Min Act: -0.0000

Data Index: 327814 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 2.0563. Min Range: -2.0563

Max Act: 1.7602. Min Act: -0.0000

Data Index: 1571397 (Python Code)

Max Activating Token Index: 686

Text #7

Max Range: 2.0563. Min Range: -2.0563

Max Act: 1.7457. Min Act: -0.0000

Data Index: 470187 (C4 (Web Text))

Max Activating Token Index: 219

Text #8

Max Range: 2.0563. Min Range: -2.0563

Max Act: 1.8049. Min Act: -0.0000

Data Index: 295537 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 2.0563. Min Range: -2.0563

Max Act: 1.9706. Min Act: -0.0000

Data Index: 1178852 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 2.0563. Min Range: -2.0563

Max Act: 1.7894. Min Act: -0.0000

Data Index: 638043 (C4 (Web Text))

Max Activating Token Index: 779

Text #11

Max Range: 2.0563. Min Range: -2.0563

Max Act: 1.6893. Min Act: -0.0000

Data Index: 1194148 (C4 (Web Text))

Max Activating Token Index: 657

Text #12

Max Range: 2.0563. Min Range: -2.0563

Max Act: 1.6636. Min Act: -0.0000

Data Index: 44023 (C4 (Web Text))

Max Activating Token Index: 992

Text #13

Max Range: 2.0563. Min Range: -2.0563

Max Act: 1.6908. Min Act: -0.0000

Data Index: 869238 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 2.0563. Min Range: -2.0563

Max Act: 1.6751. Min Act: -0.0000

Data Index: 366715 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 2.0563. Min Range: -2.0563

Max Act: 1.6707. Min Act: -0.0000

Data Index: 761023 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 2.0563. Min Range: -2.0563

Max Act: 1.6710. Min Act: -0.0000

Data Index: 239346 (C4 (Web Text))

Max Activating Token Index: 795

Text #17

Max Range: 2.0563. Min Range: -2.0563

Max Act: 1.6590. Min Act: -0.0000

Data Index: 1261225 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 2.0563. Min Range: -2.0563

Max Act: 1.6365. Min Act: -0.0000

Data Index: 408160 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 2.0563. Min Range: -2.0563

Max Act: 1.6321. Min Act: -0.0000

Data Index: 1220873 (C4 (Web Text))

Max Activating Token Index: 820