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

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

Neuron 1067 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.2133. Min Act: -0.0000

Data Index: 1376640 (Python Code)

Max Activating Token Index: 755

Text #1

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1957. Min Act: -0.0001

Data Index: 411028 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1748. Min Act: -0.0001

Data Index: 415632 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1665. Min Act: -0.0001

Data Index: 1627079 (Python Code)

Max Activating Token Index: 398

Text #4

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1664. Min Act: -0.0001

Data Index: 402502 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1736. Min Act: -0.0001

Data Index: 1587286 (Python Code)

Max Activating Token Index: 454

Text #6

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1705. Min Act: -0.0001

Data Index: 145010 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1681. Min Act: -0.0001

Data Index: 630750 (C4 (Web Text))

Max Activating Token Index: 356

Text #8

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1807. Min Act: -0.0001

Data Index: 526499 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1562. Min Act: -0.0001

Data Index: 578043 (C4 (Web Text))

Max Activating Token Index: 87

Text #10

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1508. Min Act: -0.0001

Data Index: 392670 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1500. Min Act: -0.0000

Data Index: 472070 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1834. Min Act: -0.0001

Data Index: 1118378 (C4 (Web Text))

Max Activating Token Index: 335

Text #13

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1515. Min Act: -0.0001

Data Index: 1523293 (Python Code)

Max Activating Token Index: 102

Text #14

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1460. Min Act: -0.0001

Data Index: 1070474 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1561. Min Act: -0.0001

Data Index: 538687 (C4 (Web Text))

Max Activating Token Index: 341

Text #16

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1499. Min Act: -0.0001

Data Index: 514859 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1476. Min Act: -0.0001

Data Index: 72520 (C4 (Web Text))

Max Activating Token Index: 469

Text #18

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1560. Min Act: -0.0001

Data Index: 1354681 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1349. Min Act: -0.0001

Data Index: 1297212 (C4 (Web Text))

Max Activating Token Index: 207