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

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

Neuron 4622 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2157. Min Range: -0.2157

Max Act: 0.2138. Min Act: -0.0000

Data Index: 913490 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 0.2157. Min Range: -0.2157

Max Act: 0.2157. Min Act: -0.0000

Data Index: 235665 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 0.2157. Min Range: -0.2157

Max Act: 0.1859. Min Act: -0.0000

Data Index: 583454 (C4 (Web Text))

Max Activating Token Index: 633

Text #3

Max Range: 0.2157. Min Range: -0.2157

Max Act: 0.1643. Min Act: -0.0000

Data Index: 632404 (C4 (Web Text))

Max Activating Token Index: 531

Text #4

Max Range: 0.2157. Min Range: -0.2157

Max Act: 0.1520. Min Act: -0.0000

Data Index: 912983 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 0.2157. Min Range: -0.2157

Max Act: 0.1640. Min Act: -0.0000

Data Index: 422015 (C4 (Web Text))

Max Activating Token Index: 547

Text #6

Max Range: 0.2157. Min Range: -0.2157

Max Act: 0.1380. Min Act: -0.0000

Data Index: 1482871 (Python Code)

Max Activating Token Index: 411

Text #7

Max Range: 0.2157. Min Range: -0.2157

Max Act: 0.1570. Min Act: -0.0000

Data Index: 213455 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 0.2157. Min Range: -0.2157

Max Act: 0.1455. Min Act: -0.0000

Data Index: 516997 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 0.2157. Min Range: -0.2157

Max Act: 0.1480. Min Act: -0.0000

Data Index: 229023 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 0.2157. Min Range: -0.2157

Max Act: 0.1502. Min Act: -0.0000

Data Index: 97708 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 0.2157. Min Range: -0.2157

Max Act: 0.1416. Min Act: -0.0000

Data Index: 975532 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 0.2157. Min Range: -0.2157

Max Act: 0.1389. Min Act: -0.0000

Data Index: 1115080 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 0.2157. Min Range: -0.2157

Max Act: 0.1339. Min Act: -0.0000

Data Index: 1524230 (Python Code)

Max Activating Token Index: 633

Text #14

Max Range: 0.2157. Min Range: -0.2157

Max Act: 0.1483. Min Act: -0.0000

Data Index: 884730 (C4 (Web Text))

Max Activating Token Index: 871

Text #15

Max Range: 0.2157. Min Range: -0.2157

Max Act: 0.1521. Min Act: -0.0000

Data Index: 225452 (C4 (Web Text))

Max Activating Token Index: 681

Text #16

Max Range: 0.2157. Min Range: -0.2157

Max Act: 0.1486. Min Act: -0.0000

Data Index: 778940 (C4 (Web Text))

Max Activating Token Index: 369

Text #17

Max Range: 0.2157. Min Range: -0.2157

Max Act: 0.1478. Min Act: -0.0000

Data Index: 152762 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 0.2157. Min Range: -0.2157

Max Act: 0.1455. Min Act: -0.0000

Data Index: 725527 (C4 (Web Text))

Max Activating Token Index: 282

Text #19

Max Range: 0.2157. Min Range: -0.2157

Max Act: 0.1458. Min Act: -0.0000

Data Index: 628175 (C4 (Web Text))

Max Activating Token Index: 827