Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1889 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0696. Min Act: -0.0001

Data Index: 662620 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0629. Min Act: -0.0002

Data Index: 422606 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0621. Min Act: -0.0002

Data Index: 1011189 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0605. Min Act: -0.0001

Data Index: 802256 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0599. Min Act: -0.0002

Data Index: 1179022 (C4 (Web Text))

Max Activating Token Index: 627

Text #5

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0590. Min Act: -0.0003

Data Index: 137108 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0567. Min Act: -0.0003

Data Index: 675368 (C4 (Web Text))

Max Activating Token Index: 622

Text #7

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0571. Min Act: -0.0002

Data Index: 248240 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0569. Min Act: -0.0002

Data Index: 162220 (C4 (Web Text))

Max Activating Token Index: 545

Text #9

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0551. Min Act: -0.0002

Data Index: 594082 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0549. Min Act: -0.0002

Data Index: 1204425 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0559. Min Act: -0.0003

Data Index: 547609 (C4 (Web Text))

Max Activating Token Index: 351

Text #12

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0546. Min Act: -0.0002

Data Index: 783137 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0558. Min Act: -0.0002

Data Index: 210791 (C4 (Web Text))

Max Activating Token Index: 832

Text #14

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0532. Min Act: -0.0002

Data Index: 879502 (C4 (Web Text))

Max Activating Token Index: 417

Text #15

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0533. Min Act: -0.0002

Data Index: 1256217 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0525. Min Act: -0.0003

Data Index: 1327526 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0533. Min Act: -0.0002

Data Index: 47950 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0518. Min Act: -0.0002

Data Index: 70754 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0529. Min Act: -0.0002

Data Index: 1113503 (C4 (Web Text))

Max Activating Token Index: 771