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

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

Neuron 3587 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.1014. Min Act: -0.0001

Data Index: 657888 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.1014. Min Act: -0.0001

Data Index: 364136 (C4 (Web Text))

Max Activating Token Index: 364

Text #2

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.1046. Min Act: -0.0001

Data Index: 347088 (C4 (Web Text))

Max Activating Token Index: 334

Text #3

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.1064. Min Act: -0.0001

Data Index: 555999 (C4 (Web Text))

Max Activating Token Index: 167

Text #4

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0938. Min Act: -0.0001

Data Index: 281096 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0966. Min Act: -0.0000

Data Index: 840594 (C4 (Web Text))

Max Activating Token Index: 486

Text #6

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0880. Min Act: -0.0001

Data Index: 327927 (C4 (Web Text))

Max Activating Token Index: 514

Text #7

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0911. Min Act: -0.0001

Data Index: 281556 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0909. Min Act: -0.0001

Data Index: 571040 (C4 (Web Text))

Max Activating Token Index: 169

Text #9

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0947. Min Act: -0.0001

Data Index: 544893 (C4 (Web Text))

Max Activating Token Index: 563

Text #10

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0758. Min Act: -0.0001

Data Index: 1349377 (C4 (Web Text))

Max Activating Token Index: 223

Text #11

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0867. Min Act: -0.0001

Data Index: 459572 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0922. Min Act: -0.0001

Data Index: 347495 (C4 (Web Text))

Max Activating Token Index: 841

Text #13

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0835. Min Act: -0.0001

Data Index: 897922 (C4 (Web Text))

Max Activating Token Index: 623

Text #14

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0797. Min Act: -0.0001

Data Index: 887770 (C4 (Web Text))

Max Activating Token Index: 645

Text #15

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0789. Min Act: -0.0001

Data Index: 849343 (C4 (Web Text))

Max Activating Token Index: 360

Text #16

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0842. Min Act: -0.0001

Data Index: 750695 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0821. Min Act: -0.0001

Data Index: 16246 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0779. Min Act: -0.0001

Data Index: 250299 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0823. Min Act: -0.0001

Data Index: 739721 (C4 (Web Text))

Max Activating Token Index: 378