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

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

Neuron 1434 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9827. Min Range: -1.9827

Max Act: 1.9827. Min Act: -0.0000

Data Index: 1183164 (C4 (Web Text))

Max Activating Token Index: 502

Text #1

Max Range: 1.9827. Min Range: -1.9827

Max Act: 1.6238. Min Act: -0.0000

Data Index: 1033553 (C4 (Web Text))

Max Activating Token Index: 432

Text #2

Max Range: 1.9827. Min Range: -1.9827

Max Act: 1.6880. Min Act: -0.0000

Data Index: 705493 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 1.9827. Min Range: -1.9827

Max Act: 1.0979. Min Act: -0.0000

Data Index: 1602559 (Python Code)

Max Activating Token Index: 331

Text #4

Max Range: 1.9827. Min Range: -1.9827

Max Act: 0.9654. Min Act: -0.0000

Data Index: 238187 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 1.9827. Min Range: -1.9827

Max Act: 0.9757. Min Act: -0.0000

Data Index: 377014 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 1.9827. Min Range: -1.9827

Max Act: 1.0213. Min Act: -0.0000

Data Index: 1427066 (Python Code)

Max Activating Token Index: 954

Text #7

Max Range: 1.9827. Min Range: -1.9827

Max Act: 1.0496. Min Act: -0.0000

Data Index: 829443 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 1.9827. Min Range: -1.9827

Max Act: 0.9663. Min Act: -0.0000

Data Index: 456902 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 1.9827. Min Range: -1.9827

Max Act: 0.9885. Min Act: -0.0000

Data Index: 1073589 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 1.9827. Min Range: -1.9827

Max Act: 0.9624. Min Act: -0.0000

Data Index: 1087612 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 1.9827. Min Range: -1.9827

Max Act: 0.8600. Min Act: -0.0000

Data Index: 1023799 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 1.9827. Min Range: -1.9827

Max Act: 0.8417. Min Act: -0.0000

Data Index: 350382 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 1.9827. Min Range: -1.9827

Max Act: 0.8411. Min Act: -0.0000

Data Index: 116842 (C4 (Web Text))

Max Activating Token Index: 668

Text #14

Max Range: 1.9827. Min Range: -1.9827

Max Act: 0.7668. Min Act: -0.0000

Data Index: 603994 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 1.9827. Min Range: -1.9827

Max Act: 0.8607. Min Act: -0.0000

Data Index: 443863 (C4 (Web Text))

Max Activating Token Index: 224

Text #16

Max Range: 1.9827. Min Range: -1.9827

Max Act: 0.8033. Min Act: -0.0000

Data Index: 814503 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 1.9827. Min Range: -1.9827

Max Act: 0.8485. Min Act: -0.0000

Data Index: 981841 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 1.9827. Min Range: -1.9827

Max Act: 0.8054. Min Act: -0.0000

Data Index: 575679 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 1.9827. Min Range: -1.9827

Max Act: 0.8448. Min Act: -0.0000

Data Index: 1172830 (C4 (Web Text))

Max Activating Token Index: 446