Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2691 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0998. Min Act: -0.0004

Data Index: 661173 (C4 (Web Text))

Max Activating Token Index: 938

Text #1

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0817. Min Act: -0.0004

Data Index: 494578 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0874. Min Act: -0.0004

Data Index: 400727 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0964. Min Act: -0.0004

Data Index: 407295 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0891. Min Act: -0.0004

Data Index: 978097 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0821. Min Act: -0.0004

Data Index: 224620 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0817. Min Act: -0.0004

Data Index: 143440 (C4 (Web Text))

Max Activating Token Index: 358

Text #7

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0851. Min Act: -0.0004

Data Index: 312605 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0861. Min Act: -0.0004

Data Index: 459095 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0829. Min Act: -0.0004

Data Index: 1108829 (C4 (Web Text))

Max Activating Token Index: 966

Text #10

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0791. Min Act: -0.0004

Data Index: 902147 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0794. Min Act: -0.0004

Data Index: 225320 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0849. Min Act: -0.0004

Data Index: 332481 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0784. Min Act: -0.0004

Data Index: 25220 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0785. Min Act: -0.0004

Data Index: 818919 (C4 (Web Text))

Max Activating Token Index: 831

Text #15

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0830. Min Act: -0.0004

Data Index: 277305 (C4 (Web Text))

Max Activating Token Index: 754

Text #16

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0766. Min Act: -0.0004

Data Index: 324639 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0763. Min Act: -0.0004

Data Index: 319667 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0790. Min Act: -0.0004

Data Index: 158062 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0820. Min Act: -0.0004

Data Index: 992931 (C4 (Web Text))

Max Activating Token Index: 706