Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1634 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0652. Min Act: -0.0002

Data Index: 521071 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0650. Min Act: -0.0002

Data Index: 469316 (C4 (Web Text))

Max Activating Token Index: 555

Text #2

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0629. Min Act: -0.0002

Data Index: 590192 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0592. Min Act: -0.0002

Data Index: 309338 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0572. Min Act: -0.0002

Data Index: 406813 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0560. Min Act: -0.0002

Data Index: 602061 (C4 (Web Text))

Max Activating Token Index: 613

Text #6

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0563. Min Act: -0.0002

Data Index: 1052523 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0556. Min Act: -0.0002

Data Index: 807067 (C4 (Web Text))

Max Activating Token Index: 943

Text #8

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0523. Min Act: -0.0002

Data Index: 265886 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0518. Min Act: -0.0002

Data Index: 822162 (C4 (Web Text))

Max Activating Token Index: 385

Text #10

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0529. Min Act: -0.0002

Data Index: 705914 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0507. Min Act: -0.0002

Data Index: 433017 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0541. Min Act: -0.0002

Data Index: 291524 (C4 (Web Text))

Max Activating Token Index: 708

Text #13

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0517. Min Act: -0.0002

Data Index: 1185860 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0514. Min Act: -0.0002

Data Index: 641903 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0509. Min Act: -0.0002

Data Index: 998428 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0507. Min Act: -0.0002

Data Index: 822511 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0506. Min Act: -0.0002

Data Index: 335521 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0543. Min Act: -0.0002

Data Index: 456275 (C4 (Web Text))

Max Activating Token Index: 313

Text #19

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0507. Min Act: -0.0002

Data Index: 427923 (C4 (Web Text))

Max Activating Token Index: 277