Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2533 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9410. Min Range: -0.9410

Max Act: 0.9410. Min Act: -0.0000

Data Index: 599074 (C4 (Web Text))

Max Activating Token Index: 433

Text #1

Max Range: 0.9410. Min Range: -0.9410

Max Act: 0.8853. Min Act: -0.0000

Data Index: 174759 (C4 (Web Text))

Max Activating Token Index: 888

Text #2

Max Range: 0.9410. Min Range: -0.9410

Max Act: 0.9049. Min Act: -0.0000

Data Index: 104306 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 0.9410. Min Range: -0.9410

Max Act: 0.8009. Min Act: -0.0000

Data Index: 1235366 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 0.9410. Min Range: -0.9410

Max Act: 0.7642. Min Act: -0.0000

Data Index: 1309870 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 0.9410. Min Range: -0.9410

Max Act: 0.7826. Min Act: -0.0000

Data Index: 808682 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 0.9410. Min Range: -0.9410

Max Act: 0.8054. Min Act: -0.0000

Data Index: 145203 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 0.9410. Min Range: -0.9410

Max Act: 0.7705. Min Act: -0.0000

Data Index: 1209411 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 0.9410. Min Range: -0.9410

Max Act: 0.7211. Min Act: -0.0000

Data Index: 1144136 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 0.9410. Min Range: -0.9410

Max Act: 0.7073. Min Act: -0.0000

Data Index: 1075424 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 0.9410. Min Range: -0.9410

Max Act: 0.7252. Min Act: -0.0000

Data Index: 273148 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 0.9410. Min Range: -0.9410

Max Act: 0.6847. Min Act: -0.0000

Data Index: 1350405 (C4 (Web Text))

Max Activating Token Index: 993

Text #12

Max Range: 0.9410. Min Range: -0.9410

Max Act: 0.7449. Min Act: -0.0000

Data Index: 1029450 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 0.9410. Min Range: -0.9410

Max Act: 0.7153. Min Act: -0.0000

Data Index: 1196507 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 0.9410. Min Range: -0.9410

Max Act: 0.6978. Min Act: -0.0000

Data Index: 288621 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 0.9410. Min Range: -0.9410

Max Act: 0.7169. Min Act: -0.0000

Data Index: 888491 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 0.9410. Min Range: -0.9410

Max Act: 0.7162. Min Act: -0.0000

Data Index: 1168024 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 0.9410. Min Range: -0.9410

Max Act: 0.6631. Min Act: -0.0000

Data Index: 1187136 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 0.9410. Min Range: -0.9410

Max Act: 0.7308. Min Act: -0.0000

Data Index: 307969 (C4 (Web Text))

Max Activating Token Index: 731

Text #19

Max Range: 0.9410. Min Range: -0.9410

Max Act: 0.6918. Min Act: -0.0000

Data Index: 1163458 (C4 (Web Text))

Max Activating Token Index: 383