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

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

Neuron 1198 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: 0.4866. Min Range: -0.4866

Max Act: 0.4866. Min Act: -0.0001

Data Index: 594903 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.4665. Min Act: -0.0001

Data Index: 587514 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.4149. Min Act: -0.0001

Data Index: 210640 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.4296. Min Act: -0.0001

Data Index: 685790 (C4 (Web Text))

Max Activating Token Index: 225

Text #4

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.4184. Min Act: -0.0001

Data Index: 1083561 (C4 (Web Text))

Max Activating Token Index: 172

Text #5

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.4133. Min Act: -0.0001

Data Index: 394406 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.4155. Min Act: -0.0001

Data Index: 182493 (C4 (Web Text))

Max Activating Token Index: 892

Text #7

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.4105. Min Act: -0.0001

Data Index: 716978 (C4 (Web Text))

Max Activating Token Index: 323

Text #8

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.4108. Min Act: -0.0001

Data Index: 1275721 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.4118. Min Act: -0.0001

Data Index: 509071 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.3937. Min Act: -0.0001

Data Index: 126474 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.4157. Min Act: -0.0001

Data Index: 576095 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.4049. Min Act: -0.0001

Data Index: 831767 (C4 (Web Text))

Max Activating Token Index: 872

Text #13

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.3863. Min Act: -0.0001

Data Index: 996191 (C4 (Web Text))

Max Activating Token Index: 275

Text #14

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.3784. Min Act: -0.0001

Data Index: 442205 (C4 (Web Text))

Max Activating Token Index: 313

Text #15

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.3906. Min Act: -0.0001

Data Index: 222674 (C4 (Web Text))

Max Activating Token Index: 417

Text #16

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.3882. Min Act: -0.0001

Data Index: 1048184 (C4 (Web Text))

Max Activating Token Index: 991

Text #17

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.3920. Min Act: -0.0001

Data Index: 1069716 (C4 (Web Text))

Max Activating Token Index: 651

Text #18

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.3770. Min Act: -0.0001

Data Index: 257310 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.3985. Min Act: -0.0001

Data Index: 134869 (C4 (Web Text))

Max Activating Token Index: 1023