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

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

Neuron 933 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.7415. Min Act: -0.0000

Data Index: 1461011 (Python Code)

Max Activating Token Index: 281

Text #1

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.6772. Min Act: -0.0001

Data Index: 1478236 (Python Code)

Max Activating Token Index: 389

Text #2

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.6170. Min Act: -0.0001

Data Index: 1637553 (Python Code)

Max Activating Token Index: 389

Text #3

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.6463. Min Act: -0.0001

Data Index: 1380321 (Python Code)

Max Activating Token Index: 296

Text #4

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.6119. Min Act: -0.0000

Data Index: 1392060 (Python Code)

Max Activating Token Index: 487

Text #5

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.4856. Min Act: -0.0001

Data Index: 1478398 (Python Code)

Max Activating Token Index: 368

Text #6

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.4360. Min Act: -0.0001

Data Index: 1580067 (Python Code)

Max Activating Token Index: 84

Text #7

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.4491. Min Act: -0.0001

Data Index: 1441839 (Python Code)

Max Activating Token Index: 91

Text #8

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.5216. Min Act: -0.0000

Data Index: 1377903 (Python Code)

Max Activating Token Index: 878

Text #9

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.4581. Min Act: -0.0001

Data Index: 1538124 (Python Code)

Max Activating Token Index: 340

Text #10

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.4503. Min Act: -0.0001

Data Index: 1583456 (Python Code)

Max Activating Token Index: 351

Text #11

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.4839. Min Act: -0.0001

Data Index: 935817 (C4 (Web Text))

Max Activating Token Index: 833

Text #12

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.4299. Min Act: -0.0001

Data Index: 1523106 (Python Code)

Max Activating Token Index: 349

Text #13

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.4552. Min Act: -0.0001

Data Index: 1610909 (Python Code)

Max Activating Token Index: 357

Text #14

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.4129. Min Act: -0.0001

Data Index: 1395623 (Python Code)

Max Activating Token Index: 259

Text #15

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.4473. Min Act: -0.0000

Data Index: 1509531 (Python Code)

Max Activating Token Index: 592

Text #16

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.4570. Min Act: -0.0001

Data Index: 1472009 (Python Code)

Max Activating Token Index: 366

Text #17

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.4245. Min Act: -0.0001

Data Index: 1418905 (Python Code)

Max Activating Token Index: 273

Text #18

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.4029. Min Act: -0.0001

Data Index: 1553075 (Python Code)

Max Activating Token Index: 262

Text #19

Max Range: 0.7415. Min Range: -0.7415

Max Act: 0.4652. Min Act: -0.0001

Data Index: 1393187 (Python Code)

Max Activating Token Index: 323