Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1315 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0608. Min Act: -0.0002

Data Index: 869245 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0607. Min Act: -0.0002

Data Index: 164457 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0592. Min Act: -0.0002

Data Index: 1020984 (C4 (Web Text))

Max Activating Token Index: 898

Text #3

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0581. Min Act: -0.0002

Data Index: 1272379 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0609. Min Act: -0.0002

Data Index: 918771 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0553. Min Act: -0.0002

Data Index: 86920 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0592. Min Act: -0.0002

Data Index: 112413 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0573. Min Act: -0.0002

Data Index: 294324 (C4 (Web Text))

Max Activating Token Index: 717

Text #8

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0557. Min Act: -0.0002

Data Index: 85156 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0555. Min Act: -0.0002

Data Index: 1109897 (C4 (Web Text))

Max Activating Token Index: 285

Text #10

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0558. Min Act: -0.0002

Data Index: 1040863 (C4 (Web Text))

Max Activating Token Index: 139

Text #11

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0552. Min Act: -0.0002

Data Index: 850824 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0556. Min Act: -0.0002

Data Index: 519029 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0557. Min Act: -0.0002

Data Index: 472737 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0549. Min Act: -0.0002

Data Index: 239874 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0551. Min Act: -0.0002

Data Index: 961360 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0547. Min Act: -0.0002

Data Index: 838772 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0544. Min Act: -0.0002

Data Index: 200234 (C4 (Web Text))

Max Activating Token Index: 779

Text #18

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0545. Min Act: -0.0002

Data Index: 1159360 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0532. Min Act: -0.0002

Data Index: 1035176 (C4 (Web Text))

Max Activating Token Index: 955