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

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

Neuron 1651 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: 0.0751. Min Range: -0.0751

Max Act: 0.0751. Min Act: -0.0002

Data Index: 1089206 (C4 (Web Text))

Max Activating Token Index: 351

Text #1

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0749. Min Act: -0.0002

Data Index: 1143124 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0685. Min Act: -0.0002

Data Index: 1284982 (C4 (Web Text))

Max Activating Token Index: 425

Text #3

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0700. Min Act: -0.0002

Data Index: 682350 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0670. Min Act: -0.0002

Data Index: 751604 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0691. Min Act: -0.0002

Data Index: 1293374 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0672. Min Act: -0.0002

Data Index: 393964 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0652. Min Act: -0.0002

Data Index: 334697 (C4 (Web Text))

Max Activating Token Index: 268

Text #8

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0641. Min Act: -0.0002

Data Index: 7044 (C4 (Web Text))

Max Activating Token Index: 63

Text #9

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0622. Min Act: -0.0002

Data Index: 1328882 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0622. Min Act: -0.0002

Data Index: 532826 (C4 (Web Text))

Max Activating Token Index: 259

Text #11

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0643. Min Act: -0.0002

Data Index: 598942 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0633. Min Act: -0.0002

Data Index: 104473 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0626. Min Act: -0.0002

Data Index: 1148388 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0625. Min Act: -0.0002

Data Index: 223102 (C4 (Web Text))

Max Activating Token Index: 958

Text #15

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0644. Min Act: -0.0001

Data Index: 197218 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0654. Min Act: -0.0002

Data Index: 1029766 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0622. Min Act: -0.0001

Data Index: 866746 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0628. Min Act: -0.0002

Data Index: 149797 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0627. Min Act: -0.0002

Data Index: 856609 (C4 (Web Text))

Max Activating Token Index: 525