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

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

Neuron 6085 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: 1.9573. Min Range: -1.9573

Max Act: 1.9573. Min Act: -0.0000

Data Index: 312880 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 1.9573. Min Range: -1.9573

Max Act: 1.6568. Min Act: -0.0000

Data Index: 1372039 (Python Code)

Max Activating Token Index: 816

Text #2

Max Range: 1.9573. Min Range: -1.9573

Max Act: 1.8822. Min Act: -0.0000

Data Index: 607247 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 1.9573. Min Range: -1.9573

Max Act: 1.7389. Min Act: -0.0000

Data Index: 343372 (C4 (Web Text))

Max Activating Token Index: 938

Text #4

Max Range: 1.9573. Min Range: -1.9573

Max Act: 1.7747. Min Act: -0.0000

Data Index: 409875 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 1.9573. Min Range: -1.9573

Max Act: 1.5733. Min Act: -0.0000

Data Index: 1356941 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 1.9573. Min Range: -1.9573

Max Act: 1.4809. Min Act: -0.0000

Data Index: 1133134 (C4 (Web Text))

Max Activating Token Index: 332

Text #7

Max Range: 1.9573. Min Range: -1.9573

Max Act: 1.7056. Min Act: -0.0000

Data Index: 925060 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 1.9573. Min Range: -1.9573

Max Act: 1.6922. Min Act: -0.0000

Data Index: 525456 (C4 (Web Text))

Max Activating Token Index: 633

Text #9

Max Range: 1.9573. Min Range: -1.9573

Max Act: 1.5939. Min Act: -0.0000

Data Index: 1252699 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 1.9573. Min Range: -1.9573

Max Act: 1.6583. Min Act: -0.0000

Data Index: 1300740 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 1.9573. Min Range: -1.9573

Max Act: 1.5622. Min Act: -0.0000

Data Index: 1279296 (C4 (Web Text))

Max Activating Token Index: 346

Text #12

Max Range: 1.9573. Min Range: -1.9573

Max Act: 1.5670. Min Act: -0.0000

Data Index: 203415 (C4 (Web Text))

Max Activating Token Index: 1008

Text #13

Max Range: 1.9573. Min Range: -1.9573

Max Act: 1.5526. Min Act: -0.0000

Data Index: 612062 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 1.9573. Min Range: -1.9573

Max Act: 1.4551. Min Act: -0.0000

Data Index: 620728 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 1.9573. Min Range: -1.9573

Max Act: 1.4535. Min Act: -0.0000

Data Index: 1122713 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 1.9573. Min Range: -1.9573

Max Act: 1.4267. Min Act: -0.0000

Data Index: 946620 (C4 (Web Text))

Max Activating Token Index: 372

Text #17

Max Range: 1.9573. Min Range: -1.9573

Max Act: 1.5293. Min Act: -0.0000

Data Index: 961732 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 1.9573. Min Range: -1.9573

Max Act: 1.5095. Min Act: -0.0000

Data Index: 142555 (C4 (Web Text))

Max Activating Token Index: 718

Text #19

Max Range: 1.9573. Min Range: -1.9573

Max Act: 1.5067. Min Act: -0.0000

Data Index: 1237746 (C4 (Web Text))

Max Activating Token Index: 108