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

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

Neuron 2524 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.8101. Min Act: -0.0000

Data Index: 561564 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.7717. Min Act: -0.0001

Data Index: 236681 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6857. Min Act: -0.0000

Data Index: 340246 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.7985. Min Act: -0.0000

Data Index: 7082 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.7606. Min Act: -0.0001

Data Index: 1037520 (C4 (Web Text))

Max Activating Token Index: 981

Text #5

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.7324. Min Act: -0.0000

Data Index: 791057 (C4 (Web Text))

Max Activating Token Index: 225

Text #6

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6727. Min Act: -0.0001

Data Index: 78326 (C4 (Web Text))

Max Activating Token Index: 613

Text #7

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6665. Min Act: -0.0001

Data Index: 1136148 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6928. Min Act: -0.0000

Data Index: 66451 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6982. Min Act: -0.0001

Data Index: 920168 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.5727. Min Act: -0.0001

Data Index: 639300 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6382. Min Act: -0.0001

Data Index: 744833 (C4 (Web Text))

Max Activating Token Index: 455

Text #12

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6783. Min Act: -0.0001

Data Index: 923853 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6036. Min Act: -0.0001

Data Index: 545507 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.7041. Min Act: -0.0000

Data Index: 1332558 (C4 (Web Text))

Max Activating Token Index: 725

Text #15

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6648. Min Act: -0.0001

Data Index: 1092841 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.5341. Min Act: -0.0000

Data Index: 1208908 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6150. Min Act: -0.0001

Data Index: 1314673 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6039. Min Act: -0.0000

Data Index: 559937 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.5806. Min Act: -0.0001

Data Index: 907597 (C4 (Web Text))

Max Activating Token Index: 32