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

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

Neuron 1904 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: 0.0888. Min Range: -0.0888

Max Act: 0.0888. Min Act: -0.0002

Data Index: 1066594 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0809. Min Act: -0.0001

Data Index: 1238474 (C4 (Web Text))

Max Activating Token Index: 763

Text #2

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0785. Min Act: -0.0002

Data Index: 31158 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0771. Min Act: -0.0002

Data Index: 623824 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0768. Min Act: -0.0002

Data Index: 300544 (C4 (Web Text))

Max Activating Token Index: 470

Text #5

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0791. Min Act: -0.0002

Data Index: 802868 (C4 (Web Text))

Max Activating Token Index: 409

Text #6

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0781. Min Act: -0.0002

Data Index: 34923 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0762. Min Act: -0.0002

Data Index: 1133063 (C4 (Web Text))

Max Activating Token Index: 583

Text #8

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0728. Min Act: -0.0002

Data Index: 497161 (C4 (Web Text))

Max Activating Token Index: 568

Text #9

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0721. Min Act: -0.0002

Data Index: 8109 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0729. Min Act: -0.0002

Data Index: 1293967 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0730. Min Act: -0.0002

Data Index: 534766 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0731. Min Act: -0.0002

Data Index: 362227 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0721. Min Act: -0.0002

Data Index: 880003 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0692. Min Act: -0.0002

Data Index: 313644 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0688. Min Act: -0.0001

Data Index: 427506 (C4 (Web Text))

Max Activating Token Index: 518

Text #16

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0696. Min Act: -0.0002

Data Index: 1189431 (C4 (Web Text))

Max Activating Token Index: 634

Text #17

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0672. Min Act: -0.0001

Data Index: 1339261 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0680. Min Act: -0.0001

Data Index: 78287 (C4 (Web Text))

Max Activating Token Index: 687

Text #19

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0664. Min Act: -0.0001

Data Index: 617369 (C4 (Web Text))

Max Activating Token Index: 699