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

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

Neuron 1380 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: 1.7323. Min Range: -1.7323

Max Act: 1.7323. Min Act: -0.0001

Data Index: 984981 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.6419. Min Act: -0.0001

Data Index: 1091866 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.4506. Min Act: -0.0001

Data Index: 1570018 (Python Code)

Max Activating Token Index: 723

Text #3

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.4168. Min Act: -0.0001

Data Index: 303458 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.3972. Min Act: -0.0001

Data Index: 939485 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.4147. Min Act: -0.0001

Data Index: 341791 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.4916. Min Act: -0.0001

Data Index: 1635769 (Python Code)

Max Activating Token Index: 648

Text #7

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.4918. Min Act: -0.0001

Data Index: 1619302 (Python Code)

Max Activating Token Index: 705

Text #8

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.6507. Min Act: -0.0001

Data Index: 355016 (C4 (Web Text))

Max Activating Token Index: 776

Text #9

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.3033. Min Act: -0.0001

Data Index: 1485391 (Python Code)

Max Activating Token Index: 671

Text #10

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.4107. Min Act: -0.0001

Data Index: 1520261 (Python Code)

Max Activating Token Index: 719

Text #11

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.3252. Min Act: -0.0001

Data Index: 1028563 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.2707. Min Act: -0.0001

Data Index: 1392870 (Python Code)

Max Activating Token Index: 545

Text #13

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.3790. Min Act: -0.0001

Data Index: 701124 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.3745. Min Act: -0.0001

Data Index: 1627981 (Python Code)

Max Activating Token Index: 287

Text #15

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.4144. Min Act: -0.0001

Data Index: 176008 (C4 (Web Text))

Max Activating Token Index: 309

Text #16

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.3122. Min Act: -0.0001

Data Index: 293023 (C4 (Web Text))

Max Activating Token Index: 850

Text #17

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.3644. Min Act: -0.0001

Data Index: 435679 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.3664. Min Act: -0.0001

Data Index: 1377425 (Python Code)

Max Activating Token Index: 825

Text #19

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.3466. Min Act: -0.0001

Data Index: 1361774 (Python Code)

Max Activating Token Index: 786