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

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

Neuron 3617 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.3820. Min Act: -0.0001

Data Index: 399659 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.3622. Min Act: -0.0001

Data Index: 530982 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.3850. Min Act: -0.0001

Data Index: 405681 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.3390. Min Act: -0.0001

Data Index: 889183 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.3081. Min Act: -0.0001

Data Index: 534716 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.3377. Min Act: -0.0001

Data Index: 546981 (C4 (Web Text))

Max Activating Token Index: 658

Text #6

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2975. Min Act: -0.0001

Data Index: 704336 (C4 (Web Text))

Max Activating Token Index: 388

Text #7

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.3113. Min Act: -0.0002

Data Index: 988064 (C4 (Web Text))

Max Activating Token Index: 619

Text #8

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.3223. Min Act: -0.0001

Data Index: 442801 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2923. Min Act: -0.0001

Data Index: 922989 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2718. Min Act: -0.0001

Data Index: 1333578 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.3164. Min Act: -0.0001

Data Index: 323149 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2888. Min Act: -0.0001

Data Index: 314812 (C4 (Web Text))

Max Activating Token Index: 322

Text #13

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2934. Min Act: -0.0001

Data Index: 1121436 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.3210. Min Act: -0.0001

Data Index: 1192920 (C4 (Web Text))

Max Activating Token Index: 777

Text #15

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2920. Min Act: -0.0001

Data Index: 93460 (C4 (Web Text))

Max Activating Token Index: 7

Text #16

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.3064. Min Act: -0.0001

Data Index: 159094 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2791. Min Act: -0.0001

Data Index: 1049578 (C4 (Web Text))

Max Activating Token Index: 521

Text #18

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2758. Min Act: -0.0001

Data Index: 478524 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2884. Min Act: -0.0001

Data Index: 754468 (C4 (Web Text))

Max Activating Token Index: 331