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

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

Neuron 23 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.1073. Min Act: -0.0000

Data Index: 368836 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.1043. Min Act: -0.0000

Data Index: 436131 (C4 (Web Text))

Max Activating Token Index: 835

Text #2

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0940. Min Act: -0.0000

Data Index: 993887 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.1023. Min Act: -0.0000

Data Index: 803846 (C4 (Web Text))

Max Activating Token Index: 346

Text #4

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0934. Min Act: -0.0000

Data Index: 688552 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0875. Min Act: -0.0000

Data Index: 531981 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0844. Min Act: -0.0000

Data Index: 1162036 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0805. Min Act: -0.0000

Data Index: 1349587 (C4 (Web Text))

Max Activating Token Index: 434

Text #8

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0823. Min Act: -0.0000

Data Index: 556578 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0774. Min Act: -0.0000

Data Index: 427564 (C4 (Web Text))

Max Activating Token Index: 818

Text #10

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0815. Min Act: -0.0000

Data Index: 756042 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0839. Min Act: -0.0000

Data Index: 48563 (C4 (Web Text))

Max Activating Token Index: 751

Text #12

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0806. Min Act: -0.0000

Data Index: 85852 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0811. Min Act: -0.0000

Data Index: 23889 (C4 (Web Text))

Max Activating Token Index: 653

Text #14

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0766. Min Act: -0.0000

Data Index: 1052025 (C4 (Web Text))

Max Activating Token Index: 526

Text #15

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0820. Min Act: -0.0000

Data Index: 1354784 (C4 (Web Text))

Max Activating Token Index: 965

Text #16

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0763. Min Act: -0.0000

Data Index: 1301923 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0811. Min Act: -0.0000

Data Index: 579437 (C4 (Web Text))

Max Activating Token Index: 766

Text #18

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0808. Min Act: -0.0000

Data Index: 309021 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0735. Min Act: -0.0000

Data Index: 155682 (C4 (Web Text))

Max Activating Token Index: 993