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

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

Neuron 1125 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: 0.0784. Min Range: -0.0784

Max Act: 0.0784. Min Act: -0.0002

Data Index: 374838 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0704. Min Act: -0.0002

Data Index: 1271361 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0674. Min Act: -0.0002

Data Index: 766902 (C4 (Web Text))

Max Activating Token Index: 377

Text #3

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0652. Min Act: -0.0002

Data Index: 384674 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0635. Min Act: -0.0002

Data Index: 1232175 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0620. Min Act: -0.0002

Data Index: 580519 (C4 (Web Text))

Max Activating Token Index: 1004

Text #6

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0601. Min Act: -0.0003

Data Index: 1270945 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0599. Min Act: -0.0002

Data Index: 257921 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0584. Min Act: -0.0002

Data Index: 1178770 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0581. Min Act: -0.0002

Data Index: 284842 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0572. Min Act: -0.0002

Data Index: 399112 (C4 (Web Text))

Max Activating Token Index: 623

Text #11

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0553. Min Act: -0.0002

Data Index: 323442 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0584. Min Act: -0.0002

Data Index: 1055972 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0556. Min Act: -0.0002

Data Index: 642729 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0555. Min Act: -0.0002

Data Index: 73339 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0556. Min Act: -0.0002

Data Index: 1010983 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0549. Min Act: -0.0002

Data Index: 354557 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0549. Min Act: -0.0002

Data Index: 1254152 (C4 (Web Text))

Max Activating Token Index: 664

Text #18

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0550. Min Act: -0.0002

Data Index: 845400 (C4 (Web Text))

Max Activating Token Index: 430

Text #19

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0534. Min Act: -0.0002

Data Index: 199412 (C4 (Web Text))

Max Activating Token Index: 306