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

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

Neuron 3295 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: 0.5217. Min Range: -0.5217

Max Act: 0.5217. Min Act: -0.0001

Data Index: 619907 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.4901. Min Act: -0.0001

Data Index: 355952 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.4434. Min Act: -0.0001

Data Index: 122546 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.4423. Min Act: -0.0001

Data Index: 684653 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.4486. Min Act: -0.0001

Data Index: 794205 (C4 (Web Text))

Max Activating Token Index: 733

Text #5

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.4634. Min Act: -0.0001

Data Index: 899158 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.4492. Min Act: -0.0001

Data Index: 936528 (C4 (Web Text))

Max Activating Token Index: 352

Text #7

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.4319. Min Act: -0.0001

Data Index: 1266824 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.4028. Min Act: -0.0001

Data Index: 1316004 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.3966. Min Act: -0.0001

Data Index: 218711 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.4100. Min Act: -0.0001

Data Index: 74363 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.4102. Min Act: -0.0001

Data Index: 1072429 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.4075. Min Act: -0.0001

Data Index: 931571 (C4 (Web Text))

Max Activating Token Index: 956

Text #13

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.4063. Min Act: -0.0001

Data Index: 932251 (C4 (Web Text))

Max Activating Token Index: 903

Text #14

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.4153. Min Act: -0.0001

Data Index: 1227665 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.3998. Min Act: -0.0001

Data Index: 460922 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.3976. Min Act: -0.0001

Data Index: 409731 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.3857. Min Act: -0.0001

Data Index: 762149 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.3975. Min Act: -0.0001

Data Index: 676699 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 0.5217. Min Range: -0.5217

Max Act: 0.3941. Min Act: -0.0001

Data Index: 90813 (C4 (Web Text))

Max Activating Token Index: 333