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

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

Neuron 427 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: 0.3133. Min Range: -0.3133

Max Act: 0.3133. Min Act: -0.0001

Data Index: 876674 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.3075. Min Act: -0.0001

Data Index: 1336510 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2813. Min Act: -0.0001

Data Index: 233897 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2412. Min Act: -0.0001

Data Index: 1257570 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.1558. Min Act: -0.0001

Data Index: 951255 (C4 (Web Text))

Max Activating Token Index: 654

Text #5

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.1520. Min Act: -0.0001

Data Index: 1317806 (C4 (Web Text))

Max Activating Token Index: 791

Text #6

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.1571. Min Act: -0.0001

Data Index: 98262 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.1568. Min Act: -0.0001

Data Index: 948789 (C4 (Web Text))

Max Activating Token Index: 739

Text #8

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.1479. Min Act: -0.0001

Data Index: 207784 (C4 (Web Text))

Max Activating Token Index: 605

Text #9

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.1408. Min Act: -0.0001

Data Index: 816576 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.1484. Min Act: -0.0001

Data Index: 1329807 (C4 (Web Text))

Max Activating Token Index: 918

Text #11

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.1482. Min Act: -0.0001

Data Index: 1173616 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.1484. Min Act: -0.0001

Data Index: 536001 (C4 (Web Text))

Max Activating Token Index: 108

Text #13

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.1392. Min Act: -0.0001

Data Index: 616901 (C4 (Web Text))

Max Activating Token Index: 336

Text #14

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.1428. Min Act: -0.0001

Data Index: 1269133 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.1425. Min Act: -0.0001

Data Index: 202480 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.1257. Min Act: -0.0001

Data Index: 1307937 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.1346. Min Act: -0.0001

Data Index: 1332184 (C4 (Web Text))

Max Activating Token Index: 822

Text #18

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.1301. Min Act: -0.0001

Data Index: 312218 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.1425. Min Act: -0.0001

Data Index: 211684 (C4 (Web Text))

Max Activating Token Index: 614