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

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

Neuron 4515 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4639. Min Range: -0.4639

Max Act: 0.4639. Min Act: -0.0000

Data Index: 1137364 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 0.4639. Min Range: -0.4639

Max Act: 0.3745. Min Act: -0.0000

Data Index: 874753 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 0.4639. Min Range: -0.4639

Max Act: 0.3730. Min Act: -0.0000

Data Index: 1069869 (C4 (Web Text))

Max Activating Token Index: 496

Text #3

Max Range: 0.4639. Min Range: -0.4639

Max Act: 0.3198. Min Act: -0.0000

Data Index: 978006 (C4 (Web Text))

Max Activating Token Index: 806

Text #4

Max Range: 0.4639. Min Range: -0.4639

Max Act: 0.3161. Min Act: -0.0000

Data Index: 593479 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 0.4639. Min Range: -0.4639

Max Act: 0.3144. Min Act: -0.0000

Data Index: 366506 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 0.4639. Min Range: -0.4639

Max Act: 0.3005. Min Act: -0.0000

Data Index: 975064 (C4 (Web Text))

Max Activating Token Index: 550

Text #7

Max Range: 0.4639. Min Range: -0.4639

Max Act: 0.3121. Min Act: -0.0000

Data Index: 905517 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 0.4639. Min Range: -0.4639

Max Act: 0.2838. Min Act: -0.0000

Data Index: 780041 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 0.4639. Min Range: -0.4639

Max Act: 0.2882. Min Act: 0.0000

Data Index: 900195 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 0.4639. Min Range: -0.4639

Max Act: 0.2857. Min Act: -0.0000

Data Index: 163943 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 0.4639. Min Range: -0.4639

Max Act: 0.2895. Min Act: -0.0000

Data Index: 497675 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 0.4639. Min Range: -0.4639

Max Act: 0.2862. Min Act: -0.0000

Data Index: 709138 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 0.4639. Min Range: -0.4639

Max Act: 0.2662. Min Act: -0.0000

Data Index: 384472 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 0.4639. Min Range: -0.4639

Max Act: 0.2744. Min Act: -0.0000

Data Index: 202846 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 0.4639. Min Range: -0.4639

Max Act: 0.2573. Min Act: 0.0000

Data Index: 1009909 (C4 (Web Text))

Max Activating Token Index: 942

Text #16

Max Range: 0.4639. Min Range: -0.4639

Max Act: 0.2665. Min Act: -0.0000

Data Index: 390395 (C4 (Web Text))

Max Activating Token Index: 936

Text #17

Max Range: 0.4639. Min Range: -0.4639

Max Act: 0.2795. Min Act: -0.0000

Data Index: 781397 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 0.4639. Min Range: -0.4639

Max Act: 0.2654. Min Act: -0.0000

Data Index: 735086 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 0.4639. Min Range: -0.4639

Max Act: 0.2840. Min Act: -0.0000

Data Index: 1242718 (C4 (Web Text))

Max Activating Token Index: 804