Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 772 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.7892. Min Range: -3.7892

Max Act: 3.7892. Min Act: -0.0000

Data Index: 931405 (C4 (Web Text))

Max Activating Token Index: 290

Text #1

Max Range: 3.7892. Min Range: -3.7892

Max Act: 2.5905. Min Act: -0.0000

Data Index: 458613 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 3.7892. Min Range: -3.7892

Max Act: 2.6134. Min Act: -0.0000

Data Index: 264077 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 3.7892. Min Range: -3.7892

Max Act: 2.4366. Min Act: -0.0000

Data Index: 75831 (C4 (Web Text))

Max Activating Token Index: 735

Text #4

Max Range: 3.7892. Min Range: -3.7892

Max Act: 1.5714. Min Act: -0.0000

Data Index: 1023839 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 3.7892. Min Range: -3.7892

Max Act: 2.3304. Min Act: -0.0000

Data Index: 1254026 (C4 (Web Text))

Max Activating Token Index: 799

Text #6

Max Range: 3.7892. Min Range: -3.7892

Max Act: 2.2611. Min Act: -0.0000

Data Index: 379273 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 3.7892. Min Range: -3.7892

Max Act: 2.3316. Min Act: -0.0000

Data Index: 300050 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 3.7892. Min Range: -3.7892

Max Act: 2.2153. Min Act: -0.0000

Data Index: 745059 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 3.7892. Min Range: -3.7892

Max Act: 2.0849. Min Act: -0.0000

Data Index: 1016863 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 3.7892. Min Range: -3.7892

Max Act: 2.0367. Min Act: -0.0000

Data Index: 1261724 (C4 (Web Text))

Max Activating Token Index: 593

Text #11

Max Range: 3.7892. Min Range: -3.7892

Max Act: 2.3703. Min Act: -0.0000

Data Index: 614924 (C4 (Web Text))

Max Activating Token Index: 824

Text #12

Max Range: 3.7892. Min Range: -3.7892

Max Act: 2.1102. Min Act: -0.0000

Data Index: 184333 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 3.7892. Min Range: -3.7892

Max Act: 1.9858. Min Act: -0.0000

Data Index: 1057614 (C4 (Web Text))

Max Activating Token Index: 553

Text #14

Max Range: 3.7892. Min Range: -3.7892

Max Act: 1.8767. Min Act: -0.0000

Data Index: 329411 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 3.7892. Min Range: -3.7892

Max Act: 1.8273. Min Act: -0.0000

Data Index: 1311553 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 3.7892. Min Range: -3.7892

Max Act: 1.9752. Min Act: -0.0000

Data Index: 577248 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 3.7892. Min Range: -3.7892

Max Act: 1.8534. Min Act: -0.0000

Data Index: 611687 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 3.7892. Min Range: -3.7892

Max Act: 1.9296. Min Act: -0.0000

Data Index: 983295 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 3.7892. Min Range: -3.7892

Max Act: 1.9321. Min Act: -0.0000

Data Index: 672785 (C4 (Web Text))

Max Activating Token Index: 459