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

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

Neuron 2017 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: 0.0853. Min Range: -0.0853

Max Act: 0.0853. Min Act: -0.0002

Data Index: 908415 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0763. Min Act: -0.0002

Data Index: 387318 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0738. Min Act: -0.0002

Data Index: 384998 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0665. Min Act: -0.0002

Data Index: 242839 (C4 (Web Text))

Max Activating Token Index: 159

Text #4

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0662. Min Act: -0.0002

Data Index: 1087995 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0612. Min Act: -0.0002

Data Index: 926300 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0647. Min Act: -0.0002

Data Index: 203952 (C4 (Web Text))

Max Activating Token Index: 955

Text #7

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0627. Min Act: -0.0002

Data Index: 642107 (C4 (Web Text))

Max Activating Token Index: 949

Text #8

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0550. Min Act: -0.0002

Data Index: 30300 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0592. Min Act: -0.0002

Data Index: 145274 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0571. Min Act: -0.0002

Data Index: 133011 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0568. Min Act: -0.0002

Data Index: 991829 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0561. Min Act: -0.0002

Data Index: 725619 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0531. Min Act: -0.0002

Data Index: 910020 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0545. Min Act: -0.0002

Data Index: 160913 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0518. Min Act: -0.0002

Data Index: 18691 (C4 (Web Text))

Max Activating Token Index: 847

Text #16

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0558. Min Act: -0.0002

Data Index: 1299811 (C4 (Web Text))

Max Activating Token Index: 277

Text #17

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0539. Min Act: -0.0002

Data Index: 64514 (C4 (Web Text))

Max Activating Token Index: 532

Text #18

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0555. Min Act: -0.0002

Data Index: 628127 (C4 (Web Text))

Max Activating Token Index: 685

Text #19

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0514. Min Act: -0.0002

Data Index: 928430 (C4 (Web Text))

Max Activating Token Index: 665