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

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

Neuron 3 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.1098. Min Act: -0.0000

Data Index: 327087 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.1046. Min Act: -0.0000

Data Index: 1034376 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0922. Min Act: -0.0000

Data Index: 676819 (C4 (Web Text))

Max Activating Token Index: 482

Text #3

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0947. Min Act: -0.0000

Data Index: 223172 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0877. Min Act: -0.0000

Data Index: 408373 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0875. Min Act: -0.0000

Data Index: 1024063 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0863. Min Act: -0.0000

Data Index: 218974 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0808. Min Act: -0.0000

Data Index: 1083546 (C4 (Web Text))

Max Activating Token Index: 447

Text #8

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0829. Min Act: -0.0000

Data Index: 146961 (C4 (Web Text))

Max Activating Token Index: 944

Text #9

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0881. Min Act: -0.0000

Data Index: 84953 (C4 (Web Text))

Max Activating Token Index: 791

Text #10

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0821. Min Act: -0.0000

Data Index: 965627 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0834. Min Act: -0.0000

Data Index: 745983 (C4 (Web Text))

Max Activating Token Index: 960

Text #12

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0797. Min Act: -0.0000

Data Index: 413769 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0794. Min Act: -0.0000

Data Index: 1130469 (C4 (Web Text))

Max Activating Token Index: 126

Text #14

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0751. Min Act: -0.0000

Data Index: 769866 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0803. Min Act: -0.0000

Data Index: 119134 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0728. Min Act: -0.0000

Data Index: 1286961 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0773. Min Act: -0.0000

Data Index: 596075 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0714. Min Act: -0.0000

Data Index: 786821 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0754. Min Act: -0.0000

Data Index: 206916 (C4 (Web Text))

Max Activating Token Index: 992