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

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

Neuron 1700 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: 0.6721. Min Range: -0.6721

Max Act: 0.6721. Min Act: -0.0000

Data Index: 429696 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 0.6721. Min Range: -0.6721

Max Act: 0.6581. Min Act: -0.0000

Data Index: 340985 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 0.6721. Min Range: -0.6721

Max Act: 0.6211. Min Act: -0.0000

Data Index: 752476 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 0.6721. Min Range: -0.6721

Max Act: 0.6564. Min Act: -0.0000

Data Index: 1008249 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 0.6721. Min Range: -0.6721

Max Act: 0.6007. Min Act: -0.0000

Data Index: 686844 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 0.6721. Min Range: -0.6721

Max Act: 0.5895. Min Act: -0.0000

Data Index: 835063 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 0.6721. Min Range: -0.6721

Max Act: 0.5970. Min Act: -0.0000

Data Index: 782088 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 0.6721. Min Range: -0.6721

Max Act: 0.5842. Min Act: -0.0000

Data Index: 1057175 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 0.6721. Min Range: -0.6721

Max Act: 0.5588. Min Act: -0.0000

Data Index: 393701 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 0.6721. Min Range: -0.6721

Max Act: 0.5299. Min Act: -0.0000

Data Index: 1019883 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 0.6721. Min Range: -0.6721

Max Act: 0.5841. Min Act: -0.0000

Data Index: 1269134 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 0.6721. Min Range: -0.6721

Max Act: 0.5014. Min Act: -0.0000

Data Index: 1128340 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 0.6721. Min Range: -0.6721

Max Act: 0.5032. Min Act: -0.0000

Data Index: 980069 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 0.6721. Min Range: -0.6721

Max Act: 0.5353. Min Act: -0.0000

Data Index: 276532 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 0.6721. Min Range: -0.6721

Max Act: 0.5531. Min Act: -0.0000

Data Index: 1325435 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 0.6721. Min Range: -0.6721

Max Act: 0.5385. Min Act: -0.0000

Data Index: 215301 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 0.6721. Min Range: -0.6721

Max Act: 0.5187. Min Act: -0.0000

Data Index: 649628 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 0.6721. Min Range: -0.6721

Max Act: 0.5362. Min Act: -0.0000

Data Index: 1076874 (C4 (Web Text))

Max Activating Token Index: 961

Text #18

Max Range: 0.6721. Min Range: -0.6721

Max Act: 0.5243. Min Act: -0.0000

Data Index: 297203 (C4 (Web Text))

Max Activating Token Index: 472

Text #19

Max Range: 0.6721. Min Range: -0.6721

Max Act: 0.5158. Min Act: -0.0000

Data Index: 449411 (C4 (Web Text))

Max Activating Token Index: 590