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

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

Neuron 208 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: 1.2217. Min Range: -1.2217

Max Act: 1.2217. Min Act: -0.0001

Data Index: 519703 (C4 (Web Text))

Max Activating Token Index: 429

Text #1

Max Range: 1.2217. Min Range: -1.2217

Max Act: 1.1111. Min Act: -0.0001

Data Index: 959259 (C4 (Web Text))

Max Activating Token Index: 402

Text #2

Max Range: 1.2217. Min Range: -1.2217

Max Act: 1.1744. Min Act: -0.0001

Data Index: 479514 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 1.2217. Min Range: -1.2217

Max Act: 1.0756. Min Act: -0.0001

Data Index: 184322 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 1.2217. Min Range: -1.2217

Max Act: 1.0814. Min Act: -0.0001

Data Index: 297716 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 1.2217. Min Range: -1.2217

Max Act: 1.0411. Min Act: -0.0001

Data Index: 456745 (C4 (Web Text))

Max Activating Token Index: 945

Text #6

Max Range: 1.2217. Min Range: -1.2217

Max Act: 1.0383. Min Act: -0.0001

Data Index: 986943 (C4 (Web Text))

Max Activating Token Index: 754

Text #7

Max Range: 1.2217. Min Range: -1.2217

Max Act: 0.9911. Min Act: -0.0001

Data Index: 90472 (C4 (Web Text))

Max Activating Token Index: 875

Text #8

Max Range: 1.2217. Min Range: -1.2217

Max Act: 0.9100. Min Act: -0.0001

Data Index: 1203990 (C4 (Web Text))

Max Activating Token Index: 202

Text #9

Max Range: 1.2217. Min Range: -1.2217

Max Act: 0.9171. Min Act: -0.0001

Data Index: 255023 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 1.2217. Min Range: -1.2217

Max Act: 0.9242. Min Act: -0.0001

Data Index: 430599 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 1.2217. Min Range: -1.2217

Max Act: 0.9262. Min Act: -0.0001

Data Index: 1158847 (C4 (Web Text))

Max Activating Token Index: 350

Text #12

Max Range: 1.2217. Min Range: -1.2217

Max Act: 0.9591. Min Act: -0.0001

Data Index: 167495 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 1.2217. Min Range: -1.2217

Max Act: 0.9068. Min Act: -0.0001

Data Index: 335468 (C4 (Web Text))

Max Activating Token Index: 817

Text #14

Max Range: 1.2217. Min Range: -1.2217

Max Act: 0.8643. Min Act: -0.0001

Data Index: 856124 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 1.2217. Min Range: -1.2217

Max Act: 0.9506. Min Act: -0.0001

Data Index: 112038 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 1.2217. Min Range: -1.2217

Max Act: 0.8697. Min Act: -0.0001

Data Index: 424965 (C4 (Web Text))

Max Activating Token Index: 955

Text #17

Max Range: 1.2217. Min Range: -1.2217

Max Act: 0.8575. Min Act: -0.0001

Data Index: 167028 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 1.2217. Min Range: -1.2217

Max Act: 0.8475. Min Act: -0.0001

Data Index: 796366 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 1.2217. Min Range: -1.2217

Max Act: 0.9003. Min Act: -0.0001

Data Index: 800009 (C4 (Web Text))

Max Activating Token Index: 367