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

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

Neuron 994 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7546. Min Range: -0.7546

Max Act: 0.7546. Min Act: -0.0000

Data Index: 419164 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 0.7546. Min Range: -0.7546

Max Act: 0.7004. Min Act: -0.0001

Data Index: 364030 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 0.7546. Min Range: -0.7546

Max Act: 0.6755. Min Act: -0.0000

Data Index: 627872 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 0.7546. Min Range: -0.7546

Max Act: 0.6345. Min Act: -0.0001

Data Index: 580141 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 0.7546. Min Range: -0.7546

Max Act: 0.6114. Min Act: -0.0001

Data Index: 275375 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 0.7546. Min Range: -0.7546

Max Act: 0.6078. Min Act: -0.0001

Data Index: 262557 (C4 (Web Text))

Max Activating Token Index: 982

Text #6

Max Range: 0.7546. Min Range: -0.7546

Max Act: 0.5942. Min Act: -0.0000

Data Index: 1334136 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 0.7546. Min Range: -0.7546

Max Act: 0.5611. Min Act: -0.0001

Data Index: 1153116 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 0.7546. Min Range: -0.7546

Max Act: 0.5778. Min Act: -0.0000

Data Index: 1113567 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 0.7546. Min Range: -0.7546

Max Act: 0.5246. Min Act: -0.0001

Data Index: 1177967 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 0.7546. Min Range: -0.7546

Max Act: 0.5762. Min Act: -0.0001

Data Index: 475635 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 0.7546. Min Range: -0.7546

Max Act: 0.5379. Min Act: -0.0000

Data Index: 603285 (C4 (Web Text))

Max Activating Token Index: 427

Text #12

Max Range: 0.7546. Min Range: -0.7546

Max Act: 0.5566. Min Act: -0.0001

Data Index: 1164483 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 0.7546. Min Range: -0.7546

Max Act: 0.5657. Min Act: -0.0001

Data Index: 1287324 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 0.7546. Min Range: -0.7546

Max Act: 0.5699. Min Act: -0.0001

Data Index: 1316838 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 0.7546. Min Range: -0.7546

Max Act: 0.5136. Min Act: -0.0000

Data Index: 1024674 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 0.7546. Min Range: -0.7546

Max Act: 0.5175. Min Act: -0.0000

Data Index: 549743 (C4 (Web Text))

Max Activating Token Index: 152

Text #17

Max Range: 0.7546. Min Range: -0.7546

Max Act: 0.5591. Min Act: -0.0000

Data Index: 638324 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 0.7546. Min Range: -0.7546

Max Act: 0.5396. Min Act: -0.0000

Data Index: 582223 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 0.7546. Min Range: -0.7546

Max Act: 0.5100. Min Act: -0.0001

Data Index: 893690 (C4 (Web Text))

Max Activating Token Index: 74