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

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

Neuron 950 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.9368. Min Act: -0.0001

Data Index: 844081 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.8840. Min Act: -0.0001

Data Index: 110637 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.8472. Min Act: -0.0001

Data Index: 108797 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.8163. Min Act: -0.0001

Data Index: 26529 (C4 (Web Text))

Max Activating Token Index: 509

Text #4

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7720. Min Act: -0.0001

Data Index: 1258830 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.6835. Min Act: -0.0001

Data Index: 638340 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7457. Min Act: -0.0001

Data Index: 20062 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7597. Min Act: -0.0001

Data Index: 532916 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7597. Min Act: -0.0001

Data Index: 1381380 (Python Code)

Max Activating Token Index: 537

Text #9

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7909. Min Act: -0.0001

Data Index: 252477 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7689. Min Act: -0.0001

Data Index: 956907 (C4 (Web Text))

Max Activating Token Index: 537

Text #11

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7218. Min Act: -0.0001

Data Index: 618534 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.6832. Min Act: -0.0001

Data Index: 234934 (C4 (Web Text))

Max Activating Token Index: 712

Text #13

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7344. Min Act: -0.0001

Data Index: 1068519 (C4 (Web Text))

Max Activating Token Index: 913

Text #14

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7324. Min Act: -0.0001

Data Index: 696479 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7511. Min Act: -0.0001

Data Index: 577321 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7206. Min Act: -0.0001

Data Index: 470077 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7199. Min Act: -0.0001

Data Index: 1255276 (C4 (Web Text))

Max Activating Token Index: 202

Text #18

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7032. Min Act: -0.0001

Data Index: 1196374 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 0.9368. Min Range: -0.9368

Max Act: 0.7650. Min Act: -0.0001

Data Index: 1088102 (C4 (Web Text))

Max Activating Token Index: 1004