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

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

Neuron 3648 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8003. Min Range: -0.8003

Max Act: 0.8003. Min Act: 0.0002

Data Index: 191377 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 0.8003. Min Range: -0.8003

Max Act: 0.7606. Min Act: 0.0000

Data Index: 215374 (C4 (Web Text))

Max Activating Token Index: 940

Text #2

Max Range: 0.8003. Min Range: -0.8003

Max Act: 0.7092. Min Act: -0.0001

Data Index: 845070 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 0.8003. Min Range: -0.8003

Max Act: 0.7226. Min Act: -0.0001

Data Index: 50925 (C4 (Web Text))

Max Activating Token Index: 225

Text #4

Max Range: 0.8003. Min Range: -0.8003

Max Act: 0.6948. Min Act: -0.0000

Data Index: 110805 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 0.8003. Min Range: -0.8003

Max Act: 0.7011. Min Act: -0.0001

Data Index: 225947 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 0.8003. Min Range: -0.8003

Max Act: 0.7148. Min Act: -0.0001

Data Index: 1189090 (C4 (Web Text))

Max Activating Token Index: 591

Text #7

Max Range: 0.8003. Min Range: -0.8003

Max Act: 0.6741. Min Act: -0.0000

Data Index: 939747 (C4 (Web Text))

Max Activating Token Index: 284

Text #8

Max Range: 0.8003. Min Range: -0.8003

Max Act: 0.5507. Min Act: -0.0001

Data Index: 1249477 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 0.8003. Min Range: -0.8003

Max Act: 0.6229. Min Act: -0.0001

Data Index: 114729 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 0.8003. Min Range: -0.8003

Max Act: 0.5959. Min Act: 0.0003

Data Index: 1125259 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 0.8003. Min Range: -0.8003

Max Act: 0.6146. Min Act: -0.0000

Data Index: 52338 (C4 (Web Text))

Max Activating Token Index: 553

Text #12

Max Range: 0.8003. Min Range: -0.8003

Max Act: 0.6353. Min Act: 0.0002

Data Index: 563644 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 0.8003. Min Range: -0.8003

Max Act: 0.6345. Min Act: -0.0000

Data Index: 1025510 (C4 (Web Text))

Max Activating Token Index: 572

Text #14

Max Range: 0.8003. Min Range: -0.8003

Max Act: 0.6149. Min Act: -0.0001

Data Index: 520955 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 0.8003. Min Range: -0.8003

Max Act: 0.6112. Min Act: -0.0000

Data Index: 951391 (C4 (Web Text))

Max Activating Token Index: 977

Text #16

Max Range: 0.8003. Min Range: -0.8003

Max Act: 0.5848. Min Act: -0.0001

Data Index: 1086508 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 0.8003. Min Range: -0.8003

Max Act: 0.5841. Min Act: -0.0000

Data Index: 1254545 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 0.8003. Min Range: -0.8003

Max Act: 0.6115. Min Act: -0.0000

Data Index: 1123014 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 0.8003. Min Range: -0.8003

Max Act: 0.6063. Min Act: 0.0000

Data Index: 1134544 (C4 (Web Text))

Max Activating Token Index: 773