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

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

Neuron 2575 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.1322. Min Act: -0.0001

Data Index: 1191724 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.1782. Min Act: -0.0001

Data Index: 1214793 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.1383. Min Act: -0.0001

Data Index: 1353034 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.1376. Min Act: -0.0001

Data Index: 570687 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.1234. Min Act: -0.0001

Data Index: 614252 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.1766. Min Act: -0.0001

Data Index: 868993 (C4 (Web Text))

Max Activating Token Index: 658

Text #6

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.0528. Min Act: -0.0001

Data Index: 510536 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.1035. Min Act: -0.0001

Data Index: 850000 (C4 (Web Text))

Max Activating Token Index: 955

Text #8

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.0932. Min Act: -0.0001

Data Index: 1166226 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.0668. Min Act: -0.0001

Data Index: 437625 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.0867. Min Act: -0.0001

Data Index: 395829 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.0847. Min Act: -0.0001

Data Index: 433662 (C4 (Web Text))

Max Activating Token Index: 756

Text #12

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.0480. Min Act: -0.0001

Data Index: 556449 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.9565. Min Act: -0.0001

Data Index: 1311566 (C4 (Web Text))

Max Activating Token Index: 711

Text #14

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.1020. Min Act: -0.0001

Data Index: 990496 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.0037. Min Act: -0.0001

Data Index: 353694 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.0386. Min Act: -0.0001

Data Index: 577063 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.0616. Min Act: -0.0001

Data Index: 307117 (C4 (Web Text))

Max Activating Token Index: 964

Text #18

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.9768. Min Act: -0.0001

Data Index: 693274 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.0298. Min Act: -0.0001

Data Index: 1120020 (C4 (Web Text))

Max Activating Token Index: 603