Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3927 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.8049. Min Act: -0.0001

Data Index: 591243 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.6551. Min Act: -0.0001

Data Index: 327049 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.7168. Min Act: -0.0001

Data Index: 724616 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.4115. Min Act: -0.0001

Data Index: 474389 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.3968. Min Act: -0.0001

Data Index: 378513 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.5227. Min Act: -0.0001

Data Index: 253524 (C4 (Web Text))

Max Activating Token Index: 554

Text #6

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.3344. Min Act: -0.0001

Data Index: 136156 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.5310. Min Act: -0.0001

Data Index: 947969 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.3661. Min Act: -0.0001

Data Index: 357559 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.4361. Min Act: -0.0001

Data Index: 1232247 (C4 (Web Text))

Max Activating Token Index: 963

Text #10

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.4762. Min Act: -0.0001

Data Index: 666459 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.4709. Min Act: -0.0001

Data Index: 508378 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.4454. Min Act: -0.0001

Data Index: 303073 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.5038. Min Act: -0.0001

Data Index: 1329792 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.5012. Min Act: -0.0001

Data Index: 1014062 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.4175. Min Act: -0.0001

Data Index: 811733 (C4 (Web Text))

Max Activating Token Index: 82

Text #16

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.3129. Min Act: -0.0001

Data Index: 364539 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.3976. Min Act: -0.0001

Data Index: 866672 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.3476. Min Act: -0.0001

Data Index: 400733 (C4 (Web Text))

Max Activating Token Index: 930

Text #19

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.3026. Min Act: -0.0001

Data Index: 574375 (C4 (Web Text))

Max Activating Token Index: 635