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

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

Neuron 4 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0824. Min Act: -0.0005

Data Index: 613290 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0743. Min Act: -0.0005

Data Index: 968617 (C4 (Web Text))

Max Activating Token Index: 933

Text #2

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0578. Min Act: -0.0005

Data Index: 355778 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0569. Min Act: -0.0005

Data Index: 936266 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0627. Min Act: -0.0005

Data Index: 326795 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0588. Min Act: -0.0005

Data Index: 317373 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0552. Min Act: -0.0005

Data Index: 128546 (C4 (Web Text))

Max Activating Token Index: 383

Text #7

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0571. Min Act: -0.0005

Data Index: 1258264 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0556. Min Act: -0.0005

Data Index: 36486 (C4 (Web Text))

Max Activating Token Index: 934

Text #9

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0553. Min Act: -0.0005

Data Index: 505372 (C4 (Web Text))

Max Activating Token Index: 281

Text #10

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0536. Min Act: -0.0005

Data Index: 1235788 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0509. Min Act: -0.0005

Data Index: 742176 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0542. Min Act: -0.0005

Data Index: 931717 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0509. Min Act: -0.0005

Data Index: 93078 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0571. Min Act: -0.0005

Data Index: 599609 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0534. Min Act: -0.0005

Data Index: 1094305 (C4 (Web Text))

Max Activating Token Index: 282

Text #16

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0523. Min Act: -0.0005

Data Index: 347814 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0543. Min Act: -0.0005

Data Index: 462576 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0541. Min Act: -0.0005

Data Index: 226281 (C4 (Web Text))

Max Activating Token Index: 965

Text #19

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0519. Min Act: -0.0005

Data Index: 297718 (C4 (Web Text))

Max Activating Token Index: 198