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

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

Neuron 797 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: 0.0989. Min Range: -0.0989

Max Act: 0.0989. Min Act: -0.0000

Data Index: 1468825 (Python Code)

Max Activating Token Index: 934

Text #1

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0717. Min Act: -0.0000

Data Index: 37906 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0744. Min Act: -0.0000

Data Index: 1088344 (C4 (Web Text))

Max Activating Token Index: 555

Text #3

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0761. Min Act: -0.0000

Data Index: 316415 (C4 (Web Text))

Max Activating Token Index: 809

Text #4

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0863. Min Act: -0.0000

Data Index: 1326592 (C4 (Web Text))

Max Activating Token Index: 898

Text #5

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0700. Min Act: -0.0000

Data Index: 466782 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0743. Min Act: -0.0000

Data Index: 1294873 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0718. Min Act: -0.0001

Data Index: 2614 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0686. Min Act: -0.0000

Data Index: 1197363 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0631. Min Act: -0.0001

Data Index: 1111865 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0696. Min Act: -0.0000

Data Index: 1012145 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0615. Min Act: -0.0000

Data Index: 1128440 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0696. Min Act: -0.0000

Data Index: 567908 (C4 (Web Text))

Max Activating Token Index: 826

Text #13

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0600. Min Act: -0.0000

Data Index: 1204764 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0637. Min Act: -0.0000

Data Index: 820292 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0648. Min Act: -0.0000

Data Index: 842504 (C4 (Web Text))

Max Activating Token Index: 444

Text #16

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0668. Min Act: -0.0000

Data Index: 88728 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0635. Min Act: -0.0001

Data Index: 606070 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0633. Min Act: -0.0000

Data Index: 1612503 (Python Code)

Max Activating Token Index: 548

Text #19

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0608. Min Act: -0.0000

Data Index: 1144170 (C4 (Web Text))

Max Activating Token Index: 68