Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 434 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.9834. Min Range: -1.9834

Max Act: 1.9834. Min Act: -0.0001

Data Index: 122076 (C4 (Web Text))

Max Activating Token Index: 933

Text #1

Max Range: 1.9834. Min Range: -1.9834

Max Act: 1.9026. Min Act: -0.0001

Data Index: 1308760 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 1.9834. Min Range: -1.9834

Max Act: 1.8136. Min Act: -0.0001

Data Index: 713164 (C4 (Web Text))

Max Activating Token Index: 581

Text #3

Max Range: 1.9834. Min Range: -1.9834

Max Act: 1.8487. Min Act: -0.0001

Data Index: 719912 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 1.9834. Min Range: -1.9834

Max Act: 1.5888. Min Act: -0.0001

Data Index: 642449 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 1.9834. Min Range: -1.9834

Max Act: 1.5609. Min Act: -0.0001

Data Index: 216727 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 1.9834. Min Range: -1.9834

Max Act: 1.4741. Min Act: -0.0001

Data Index: 1153138 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 1.9834. Min Range: -1.9834

Max Act: 1.4282. Min Act: -0.0001

Data Index: 667244 (C4 (Web Text))

Max Activating Token Index: 1012

Text #8

Max Range: 1.9834. Min Range: -1.9834

Max Act: 1.4266. Min Act: -0.0001

Data Index: 249854 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 1.9834. Min Range: -1.9834

Max Act: 1.4225. Min Act: -0.0001

Data Index: 603734 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 1.9834. Min Range: -1.9834

Max Act: 1.4718. Min Act: -0.0001

Data Index: 1341855 (C4 (Web Text))

Max Activating Token Index: 766

Text #11

Max Range: 1.9834. Min Range: -1.9834

Max Act: 1.7328. Min Act: -0.0001

Data Index: 773129 (C4 (Web Text))

Max Activating Token Index: 263

Text #12

Max Range: 1.9834. Min Range: -1.9834

Max Act: 1.5269. Min Act: -0.0001

Data Index: 156614 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 1.9834. Min Range: -1.9834

Max Act: 1.6155. Min Act: -0.0001

Data Index: 954589 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 1.9834. Min Range: -1.9834

Max Act: 1.4167. Min Act: -0.0001

Data Index: 762780 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 1.9834. Min Range: -1.9834

Max Act: 1.5068. Min Act: -0.0001

Data Index: 657504 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 1.9834. Min Range: -1.9834

Max Act: 1.5720. Min Act: -0.0001

Data Index: 676527 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 1.9834. Min Range: -1.9834

Max Act: 1.2136. Min Act: -0.0001

Data Index: 869294 (C4 (Web Text))

Max Activating Token Index: 945

Text #18

Max Range: 1.9834. Min Range: -1.9834

Max Act: 1.2243. Min Act: -0.0001

Data Index: 1260412 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 1.9834. Min Range: -1.9834

Max Act: 1.3736. Min Act: -0.0001

Data Index: 476490 (C4 (Web Text))

Max Activating Token Index: 774