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

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

Neuron 5587 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: 0.1036. Min Range: -0.1036

Max Act: 0.1036. Min Act: -0.0002

Data Index: 156336 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0880. Min Act: -0.0002

Data Index: 827110 (C4 (Web Text))

Max Activating Token Index: 682

Text #2

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0975. Min Act: -0.0002

Data Index: 761061 (C4 (Web Text))

Max Activating Token Index: 298

Text #3

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0928. Min Act: -0.0002

Data Index: 132954 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0893. Min Act: -0.0002

Data Index: 231139 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0885. Min Act: -0.0002

Data Index: 611755 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0887. Min Act: -0.0002

Data Index: 855692 (C4 (Web Text))

Max Activating Token Index: 978

Text #7

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0872. Min Act: -0.0002

Data Index: 1238147 (C4 (Web Text))

Max Activating Token Index: 883

Text #8

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0869. Min Act: -0.0002

Data Index: 620000 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0837. Min Act: -0.0002

Data Index: 896381 (C4 (Web Text))

Max Activating Token Index: 764

Text #10

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0836. Min Act: -0.0002

Data Index: 73765 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0889. Min Act: -0.0002

Data Index: 348577 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0857. Min Act: -0.0002

Data Index: 667940 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0862. Min Act: -0.0002

Data Index: 691050 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0830. Min Act: -0.0002

Data Index: 916247 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0825. Min Act: -0.0002

Data Index: 702443 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0851. Min Act: -0.0002

Data Index: 510427 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0782. Min Act: -0.0002

Data Index: 16799 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0808. Min Act: -0.0002

Data Index: 1425462 (Python Code)

Max Activating Token Index: 208

Text #19

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0785. Min Act: -0.0002

Data Index: 18247 (C4 (Web Text))

Max Activating Token Index: 657