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

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

Neuron 5877 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7766. Min Range: -2.7766

Max Act: 2.7766. Min Act: -0.0000

Data Index: 1298992 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 2.7766. Min Range: -2.7766

Max Act: 2.7554. Min Act: -0.0000

Data Index: 1061851 (C4 (Web Text))

Max Activating Token Index: 370

Text #2

Max Range: 2.7766. Min Range: -2.7766

Max Act: 2.5868. Min Act: -0.0000

Data Index: 776947 (C4 (Web Text))

Max Activating Token Index: 706

Text #3

Max Range: 2.7766. Min Range: -2.7766

Max Act: 2.4106. Min Act: -0.0000

Data Index: 562016 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 2.7766. Min Range: -2.7766

Max Act: 2.4689. Min Act: -0.0000

Data Index: 22279 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 2.7766. Min Range: -2.7766

Max Act: 2.3250. Min Act: -0.0000

Data Index: 995866 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 2.7766. Min Range: -2.7766

Max Act: 2.4510. Min Act: -0.0000

Data Index: 863569 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 2.7766. Min Range: -2.7766

Max Act: 2.3083. Min Act: -0.0000

Data Index: 1306285 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 2.7766. Min Range: -2.7766

Max Act: 2.4102. Min Act: -0.0000

Data Index: 859773 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 2.7766. Min Range: -2.7766

Max Act: 2.3082. Min Act: -0.0000

Data Index: 365630 (C4 (Web Text))

Max Activating Token Index: 865

Text #10

Max Range: 2.7766. Min Range: -2.7766

Max Act: 2.2825. Min Act: -0.0000

Data Index: 164105 (C4 (Web Text))

Max Activating Token Index: 967

Text #11

Max Range: 2.7766. Min Range: -2.7766

Max Act: 2.2424. Min Act: -0.0000

Data Index: 651758 (C4 (Web Text))

Max Activating Token Index: 321

Text #12

Max Range: 2.7766. Min Range: -2.7766

Max Act: 2.2510. Min Act: -0.0000

Data Index: 202482 (C4 (Web Text))

Max Activating Token Index: 296

Text #13

Max Range: 2.7766. Min Range: -2.7766

Max Act: 2.0885. Min Act: -0.0000

Data Index: 474530 (C4 (Web Text))

Max Activating Token Index: 693

Text #14

Max Range: 2.7766. Min Range: -2.7766

Max Act: 2.2047. Min Act: -0.0000

Data Index: 330255 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 2.7766. Min Range: -2.7766

Max Act: 2.0821. Min Act: -0.0000

Data Index: 190554 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 2.7766. Min Range: -2.7766

Max Act: 2.3079. Min Act: -0.0000

Data Index: 347837 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 2.7766. Min Range: -2.7766

Max Act: 2.1696. Min Act: -0.0000

Data Index: 896018 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 2.7766. Min Range: -2.7766

Max Act: 2.3022. Min Act: -0.0000

Data Index: 875739 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 2.7766. Min Range: -2.7766

Max Act: 2.1639. Min Act: -0.0000

Data Index: 238363 (C4 (Web Text))

Max Activating Token Index: 809