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

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

Neuron 4197 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1788. Min Range: -2.1788

Max Act: 2.1788. Min Act: -0.0000

Data Index: 468877 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 2.1788. Min Range: -2.1788

Max Act: 2.0645. Min Act: -0.0000

Data Index: 1291234 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 2.1788. Min Range: -2.1788

Max Act: 1.9618. Min Act: -0.0000

Data Index: 365097 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 2.1788. Min Range: -2.1788

Max Act: 2.0241. Min Act: -0.0000

Data Index: 1313042 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 2.1788. Min Range: -2.1788

Max Act: 2.0254. Min Act: -0.0000

Data Index: 245980 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 2.1788. Min Range: -2.1788

Max Act: 1.8022. Min Act: -0.0000

Data Index: 655387 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 2.1788. Min Range: -2.1788

Max Act: 1.6485. Min Act: -0.0000

Data Index: 1202334 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 2.1788. Min Range: -2.1788

Max Act: 1.9694. Min Act: -0.0000

Data Index: 1605422 (Python Code)

Max Activating Token Index: 498

Text #8

Max Range: 2.1788. Min Range: -2.1788

Max Act: 1.7476. Min Act: -0.0000

Data Index: 1434446 (Python Code)

Max Activating Token Index: 353

Text #9

Max Range: 2.1788. Min Range: -2.1788

Max Act: 1.8286. Min Act: -0.0000

Data Index: 1518213 (Python Code)

Max Activating Token Index: 391

Text #10

Max Range: 2.1788. Min Range: -2.1788

Max Act: 1.9239. Min Act: -0.0000

Data Index: 1597805 (Python Code)

Max Activating Token Index: 390

Text #11

Max Range: 2.1788. Min Range: -2.1788

Max Act: 1.6424. Min Act: -0.0000

Data Index: 1373862 (Python Code)

Max Activating Token Index: 290

Text #12

Max Range: 2.1788. Min Range: -2.1788

Max Act: 1.7959. Min Act: -0.0000

Data Index: 1653794 (Python Code)

Max Activating Token Index: 228

Text #13

Max Range: 2.1788. Min Range: -2.1788

Max Act: 1.8099. Min Act: -0.0000

Data Index: 1467428 (Python Code)

Max Activating Token Index: 332

Text #14

Max Range: 2.1788. Min Range: -2.1788

Max Act: 1.8208. Min Act: -0.0000

Data Index: 1567935 (Python Code)

Max Activating Token Index: 304

Text #15

Max Range: 2.1788. Min Range: -2.1788

Max Act: 1.7399. Min Act: -0.0000

Data Index: 1604835 (Python Code)

Max Activating Token Index: 461

Text #16

Max Range: 2.1788. Min Range: -2.1788

Max Act: 1.7111. Min Act: -0.0000

Data Index: 1153950 (C4 (Web Text))

Max Activating Token Index: 387

Text #17

Max Range: 2.1788. Min Range: -2.1788

Max Act: 1.7120. Min Act: -0.0000

Data Index: 119528 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 2.1788. Min Range: -2.1788

Max Act: 1.6322. Min Act: -0.0000

Data Index: 1571430 (Python Code)

Max Activating Token Index: 427

Text #19

Max Range: 2.1788. Min Range: -2.1788

Max Act: 1.7133. Min Act: -0.0000

Data Index: 1419337 (Python Code)

Max Activating Token Index: 227