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

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

Neuron 2260 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0741. Min Act: -0.0002

Data Index: 135042 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0652. Min Act: -0.0002

Data Index: 703221 (C4 (Web Text))

Max Activating Token Index: 313

Text #2

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0564. Min Act: -0.0002

Data Index: 154865 (C4 (Web Text))

Max Activating Token Index: 805

Text #3

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0557. Min Act: -0.0002

Data Index: 1245449 (C4 (Web Text))

Max Activating Token Index: 293

Text #4

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0507. Min Act: -0.0002

Data Index: 532776 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0508. Min Act: -0.0002

Data Index: 1210588 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0486. Min Act: -0.0002

Data Index: 645997 (C4 (Web Text))

Max Activating Token Index: 417

Text #7

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0494. Min Act: -0.0002

Data Index: 1371190 (Python Code)

Max Activating Token Index: 383

Text #8

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0539. Min Act: -0.0002

Data Index: 1188004 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0474. Min Act: -0.0003

Data Index: 559500 (C4 (Web Text))

Max Activating Token Index: 735

Text #10

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0469. Min Act: -0.0002

Data Index: 469624 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0424. Min Act: -0.0002

Data Index: 1375295 (Python Code)

Max Activating Token Index: 819

Text #12

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0441. Min Act: -0.0002

Data Index: 4364 (C4 (Web Text))

Max Activating Token Index: 633

Text #13

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0469. Min Act: -0.0002

Data Index: 1235380 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0476. Min Act: -0.0002

Data Index: 504582 (C4 (Web Text))

Max Activating Token Index: 669

Text #15

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0443. Min Act: -0.0002

Data Index: 375095 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0420. Min Act: -0.0002

Data Index: 1281011 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0419. Min Act: -0.0002

Data Index: 1573502 (Python Code)

Max Activating Token Index: 323

Text #18

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0432. Min Act: -0.0002

Data Index: 286427 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0427. Min Act: -0.0002

Data Index: 226240 (C4 (Web Text))

Max Activating Token Index: 185