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

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

Neuron 224 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2600. Min Range: -5.2600

Max Act: 5.2600. Min Act: -0.0001

Data Index: 561595 (C4 (Web Text))

Max Activating Token Index: 1010

Text #1

Max Range: 5.2600. Min Range: -5.2600

Max Act: 4.1441. Min Act: -0.0001

Data Index: 1315633 (C4 (Web Text))

Max Activating Token Index: 981

Text #2

Max Range: 5.2600. Min Range: -5.2600

Max Act: 4.1767. Min Act: -0.0001

Data Index: 800711 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 5.2600. Min Range: -5.2600

Max Act: 4.1628. Min Act: -0.0001

Data Index: 930750 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 5.2600. Min Range: -5.2600

Max Act: 4.1423. Min Act: -0.0001

Data Index: 428564 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 5.2600. Min Range: -5.2600

Max Act: 4.4130. Min Act: -0.0001

Data Index: 1304060 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 5.2600. Min Range: -5.2600

Max Act: 4.1899. Min Act: -0.0001

Data Index: 769629 (C4 (Web Text))

Max Activating Token Index: 506

Text #7

Max Range: 5.2600. Min Range: -5.2600

Max Act: 4.1693. Min Act: -0.0001

Data Index: 908915 (C4 (Web Text))

Max Activating Token Index: 268

Text #8

Max Range: 5.2600. Min Range: -5.2600

Max Act: 4.3087. Min Act: -0.0000

Data Index: 996951 (C4 (Web Text))

Max Activating Token Index: 643

Text #9

Max Range: 5.2600. Min Range: -5.2600

Max Act: 4.1425. Min Act: -0.0000

Data Index: 503291 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 5.2600. Min Range: -5.2600

Max Act: 4.1897. Min Act: -0.0001

Data Index: 982183 (C4 (Web Text))

Max Activating Token Index: 920

Text #11

Max Range: 5.2600. Min Range: -5.2600

Max Act: 3.9846. Min Act: -0.0001

Data Index: 1092733 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 5.2600. Min Range: -5.2600

Max Act: 4.1862. Min Act: -0.0001

Data Index: 816593 (C4 (Web Text))

Max Activating Token Index: 728

Text #13

Max Range: 5.2600. Min Range: -5.2600

Max Act: 3.6817. Min Act: -0.0001

Data Index: 240455 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 5.2600. Min Range: -5.2600

Max Act: 3.9912. Min Act: -0.0001

Data Index: 1045246 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 5.2600. Min Range: -5.2600

Max Act: 3.6398. Min Act: -0.0001

Data Index: 315953 (C4 (Web Text))

Max Activating Token Index: 231

Text #16

Max Range: 5.2600. Min Range: -5.2600

Max Act: 3.7637. Min Act: -0.0001

Data Index: 649960 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 5.2600. Min Range: -5.2600

Max Act: 3.9242. Min Act: -0.0000

Data Index: 55557 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 5.2600. Min Range: -5.2600

Max Act: 3.7423. Min Act: -0.0001

Data Index: 255576 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 5.2600. Min Range: -5.2600

Max Act: 3.7354. Min Act: -0.0001

Data Index: 721437 (C4 (Web Text))

Max Activating Token Index: 317