Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1674 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0795. Min Act: -0.0002

Data Index: 211873 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0842. Min Act: -0.0002

Data Index: 1015971 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0906. Min Act: -0.0002

Data Index: 52528 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0887. Min Act: -0.0002

Data Index: 1000154 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0880. Min Act: -0.0002

Data Index: 1151407 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0859. Min Act: -0.0002

Data Index: 731391 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0804. Min Act: -0.0002

Data Index: 259141 (C4 (Web Text))

Max Activating Token Index: 436

Text #7

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0834. Min Act: -0.0002

Data Index: 76088 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0764. Min Act: -0.0002

Data Index: 1175781 (C4 (Web Text))

Max Activating Token Index: 666

Text #9

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0801. Min Act: -0.0002

Data Index: 1296180 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0816. Min Act: -0.0002

Data Index: 56060 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0722. Min Act: -0.0002

Data Index: 1132802 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0717. Min Act: -0.0002

Data Index: 640356 (C4 (Web Text))

Max Activating Token Index: 235

Text #13

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0758. Min Act: -0.0002

Data Index: 770167 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0728. Min Act: -0.0002

Data Index: 1286716 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0716. Min Act: -0.0002

Data Index: 1286388 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0690. Min Act: -0.0002

Data Index: 1104441 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0686. Min Act: -0.0002

Data Index: 381126 (C4 (Web Text))

Max Activating Token Index: 918

Text #18

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0700. Min Act: -0.0002

Data Index: 380887 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 0.0906. Min Range: -0.0906

Max Act: 0.0731. Min Act: -0.0002

Data Index: 597320 (C4 (Web Text))

Max Activating Token Index: 958