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

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

Neuron 1523 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.4018. Min Act: -0.0000

Data Index: 45293 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.3377. Min Act: -0.0000

Data Index: 538856 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.3315. Min Act: -0.0000

Data Index: 474723 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.3055. Min Act: -0.0000

Data Index: 393916 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.3071. Min Act: -0.0000

Data Index: 206402 (C4 (Web Text))

Max Activating Token Index: 441

Text #5

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.3031. Min Act: -0.0000

Data Index: 831100 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.3094. Min Act: -0.0000

Data Index: 184737 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.3036. Min Act: -0.0000

Data Index: 396091 (C4 (Web Text))

Max Activating Token Index: 918

Text #8

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.2857. Min Act: -0.0000

Data Index: 722061 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.2759. Min Act: -0.0000

Data Index: 1313943 (C4 (Web Text))

Max Activating Token Index: 1004

Text #10

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.2786. Min Act: -0.0000

Data Index: 1060409 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.2824. Min Act: -0.0000

Data Index: 535884 (C4 (Web Text))

Max Activating Token Index: 303

Text #12

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.2833. Min Act: -0.0000

Data Index: 601954 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.2844. Min Act: -0.0000

Data Index: 73546 (C4 (Web Text))

Max Activating Token Index: 449

Text #14

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.2885. Min Act: -0.0000

Data Index: 960248 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.2786. Min Act: -0.0000

Data Index: 1278581 (C4 (Web Text))

Max Activating Token Index: 663

Text #16

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.2647. Min Act: -0.0000

Data Index: 528276 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.2863. Min Act: -0.0000

Data Index: 581996 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.2715. Min Act: -0.0000

Data Index: 84499 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.2795. Min Act: -0.0000

Data Index: 928377 (C4 (Web Text))

Max Activating Token Index: 763