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

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

Neuron 3127 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.9030. Min Act: 0.0000

Data Index: 552821 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.5261. Min Act: -0.0000

Data Index: 61994 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.6998. Min Act: 0.0000

Data Index: 175558 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.6703. Min Act: 0.0000

Data Index: 1067388 (C4 (Web Text))

Max Activating Token Index: 326

Text #4

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.6476. Min Act: 0.0000

Data Index: 611213 (C4 (Web Text))

Max Activating Token Index: 1019

Text #5

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.6081. Min Act: 0.0000

Data Index: 1171548 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.5992. Min Act: 0.0000

Data Index: 1288372 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.5970. Min Act: 0.0000

Data Index: 859759 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.6142. Min Act: 0.0000

Data Index: 659743 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.6078. Min Act: -0.0000

Data Index: 1282021 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.5975. Min Act: -0.0000

Data Index: 372713 (C4 (Web Text))

Max Activating Token Index: 878

Text #11

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.5722. Min Act: -0.0000

Data Index: 820797 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.5914. Min Act: 0.0000

Data Index: 467620 (C4 (Web Text))

Max Activating Token Index: 892

Text #13

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.5745. Min Act: -0.0000

Data Index: 749826 (C4 (Web Text))

Max Activating Token Index: 463

Text #14

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.5814. Min Act: -0.0000

Data Index: 70988 (C4 (Web Text))

Max Activating Token Index: 510

Text #15

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.5655. Min Act: 0.0000

Data Index: 1222155 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.5820. Min Act: -0.0000

Data Index: 390814 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.6138. Min Act: 0.0000

Data Index: 1181393 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.5611. Min Act: 0.0000

Data Index: 400683 (C4 (Web Text))

Max Activating Token Index: 813

Text #19

Max Range: 0.9030. Min Range: -0.9030

Max Act: 0.5654. Min Act: -0.0000

Data Index: 1289641 (C4 (Web Text))

Max Activating Token Index: 261