Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2996 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0829. Min Act: -0.0001

Data Index: 892487 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0709. Min Act: -0.0001

Data Index: 1173618 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0750. Min Act: -0.0001

Data Index: 236824 (C4 (Web Text))

Max Activating Token Index: 317

Text #3

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0803. Min Act: -0.0001

Data Index: 205511 (C4 (Web Text))

Max Activating Token Index: 847

Text #4

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0814. Min Act: -0.0001

Data Index: 1142155 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0814. Min Act: -0.0001

Data Index: 296847 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0778. Min Act: -0.0001

Data Index: 94039 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0711. Min Act: -0.0001

Data Index: 1278058 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0817. Min Act: -0.0001

Data Index: 886566 (C4 (Web Text))

Max Activating Token Index: 854

Text #9

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0720. Min Act: -0.0001

Data Index: 1188797 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0741. Min Act: -0.0001

Data Index: 1249813 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0730. Min Act: -0.0001

Data Index: 1155711 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0697. Min Act: -0.0001

Data Index: 628254 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0711. Min Act: -0.0001

Data Index: 540128 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0736. Min Act: -0.0001

Data Index: 632545 (C4 (Web Text))

Max Activating Token Index: 513

Text #15

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0702. Min Act: -0.0001

Data Index: 780649 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0686. Min Act: -0.0001

Data Index: 170162 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0658. Min Act: -0.0001

Data Index: 932143 (C4 (Web Text))

Max Activating Token Index: 970

Text #18

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0703. Min Act: -0.0001

Data Index: 890495 (C4 (Web Text))

Max Activating Token Index: 568

Text #19

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0662. Min Act: -0.0001

Data Index: 1346771 (C4 (Web Text))

Max Activating Token Index: 773