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

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

Neuron 619 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: 4.7008. Min Range: -4.7008

Max Act: 4.7008. Min Act: -0.0000

Data Index: 61681 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 4.7008. Min Range: -4.7008

Max Act: 4.3073. Min Act: -0.0000

Data Index: 121596 (C4 (Web Text))

Max Activating Token Index: 642

Text #2

Max Range: 4.7008. Min Range: -4.7008

Max Act: 4.0144. Min Act: -0.0000

Data Index: 244258 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 4.7008. Min Range: -4.7008

Max Act: 4.1617. Min Act: -0.0000

Data Index: 236674 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 4.7008. Min Range: -4.7008

Max Act: 4.1330. Min Act: -0.0000

Data Index: 276410 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 4.7008. Min Range: -4.7008

Max Act: 3.9579. Min Act: -0.0000

Data Index: 807046 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 4.7008. Min Range: -4.7008

Max Act: 3.4992. Min Act: -0.0000

Data Index: 1232931 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 4.7008. Min Range: -4.7008

Max Act: 3.5240. Min Act: -0.0000

Data Index: 160016 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 4.7008. Min Range: -4.7008

Max Act: 3.4841. Min Act: -0.0000

Data Index: 670756 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 4.7008. Min Range: -4.7008

Max Act: 3.4288. Min Act: -0.0000

Data Index: 978039 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 4.7008. Min Range: -4.7008

Max Act: 3.1997. Min Act: -0.0000

Data Index: 48385 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 4.7008. Min Range: -4.7008

Max Act: 3.2263. Min Act: -0.0000

Data Index: 847661 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 4.7008. Min Range: -4.7008

Max Act: 2.7597. Min Act: -0.0000

Data Index: 424393 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 4.7008. Min Range: -4.7008

Max Act: 2.9878. Min Act: -0.0000

Data Index: 359570 (C4 (Web Text))

Max Activating Token Index: 163

Text #14

Max Range: 4.7008. Min Range: -4.7008

Max Act: 2.8804. Min Act: -0.0000

Data Index: 1304425 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 4.7008. Min Range: -4.7008

Max Act: 2.8389. Min Act: -0.0000

Data Index: 475688 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 4.7008. Min Range: -4.7008

Max Act: 2.7051. Min Act: -0.0000

Data Index: 139815 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 4.7008. Min Range: -4.7008

Max Act: 2.6596. Min Act: -0.0000

Data Index: 822371 (C4 (Web Text))

Max Activating Token Index: 835

Text #18

Max Range: 4.7008. Min Range: -4.7008

Max Act: 2.7953. Min Act: -0.0000

Data Index: 101855 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 4.7008. Min Range: -4.7008

Max Act: 2.7970. Min Act: -0.0000

Data Index: 962564 (C4 (Web Text))

Max Activating Token Index: 39