Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2679 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2147. Min Range: -0.2147

Max Act: 0.2082. Min Act: -0.0001

Data Index: 648397 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 0.2147. Min Range: -0.2147

Max Act: 0.1782. Min Act: -0.0001

Data Index: 124659 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 0.2147. Min Range: -0.2147

Max Act: 0.2119. Min Act: -0.0001

Data Index: 635095 (C4 (Web Text))

Max Activating Token Index: 169

Text #3

Max Range: 0.2147. Min Range: -0.2147

Max Act: 0.2008. Min Act: -0.0001

Data Index: 1054730 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 0.2147. Min Range: -0.2147

Max Act: 0.2147. Min Act: -0.0001

Data Index: 498836 (C4 (Web Text))

Max Activating Token Index: 394

Text #5

Max Range: 0.2147. Min Range: -0.2147

Max Act: 0.1925. Min Act: -0.0001

Data Index: 1112418 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 0.2147. Min Range: -0.2147

Max Act: 0.1875. Min Act: -0.0001

Data Index: 1137081 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 0.2147. Min Range: -0.2147

Max Act: 0.1797. Min Act: -0.0001

Data Index: 412024 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 0.2147. Min Range: -0.2147

Max Act: 0.1774. Min Act: -0.0001

Data Index: 623768 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 0.2147. Min Range: -0.2147

Max Act: 0.1786. Min Act: -0.0001

Data Index: 1287837 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 0.2147. Min Range: -0.2147

Max Act: 0.1850. Min Act: -0.0001

Data Index: 48445 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 0.2147. Min Range: -0.2147

Max Act: 0.1742. Min Act: -0.0001

Data Index: 900325 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 0.2147. Min Range: -0.2147

Max Act: 0.1778. Min Act: -0.0001

Data Index: 377031 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 0.2147. Min Range: -0.2147

Max Act: 0.1616. Min Act: -0.0001

Data Index: 855120 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 0.2147. Min Range: -0.2147

Max Act: 0.1518. Min Act: -0.0001

Data Index: 360207 (C4 (Web Text))

Max Activating Token Index: 806

Text #15

Max Range: 0.2147. Min Range: -0.2147

Max Act: 0.1622. Min Act: -0.0001

Data Index: 1125325 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 0.2147. Min Range: -0.2147

Max Act: 0.1372. Min Act: -0.0001

Data Index: 755181 (C4 (Web Text))

Max Activating Token Index: 821

Text #17

Max Range: 0.2147. Min Range: -0.2147

Max Act: 0.1488. Min Act: -0.0001

Data Index: 254628 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 0.2147. Min Range: -0.2147

Max Act: 0.1367. Min Act: -0.0001

Data Index: 287316 (C4 (Web Text))

Max Activating Token Index: 492

Text #19

Max Range: 0.2147. Min Range: -0.2147

Max Act: 0.1442. Min Act: -0.0001

Data Index: 882233 (C4 (Web Text))

Max Activating Token Index: 279