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

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

Neuron 20 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: 0.8518. Min Range: -0.8518

Max Act: 0.8518. Min Act: -0.0001

Data Index: 1552110 (Python Code)

Max Activating Token Index: 124

Text #1

Max Range: 0.8518. Min Range: -0.8518

Max Act: 0.8499. Min Act: -0.0001

Data Index: 1387117 (Python Code)

Max Activating Token Index: 15

Text #2

Max Range: 0.8518. Min Range: -0.8518

Max Act: 0.8367. Min Act: -0.0001

Data Index: 1360279 (Python Code)

Max Activating Token Index: 27

Text #3

Max Range: 0.8518. Min Range: -0.8518

Max Act: 0.8335. Min Act: -0.0001

Data Index: 1561909 (Python Code)

Max Activating Token Index: 709

Text #4

Max Range: 0.8518. Min Range: -0.8518

Max Act: 0.7697. Min Act: -0.0001

Data Index: 1632573 (Python Code)

Max Activating Token Index: 80

Text #5

Max Range: 0.8518. Min Range: -0.8518

Max Act: 0.7583. Min Act: -0.0001

Data Index: 1578759 (Python Code)

Max Activating Token Index: 479

Text #6

Max Range: 0.8518. Min Range: -0.8518

Max Act: 0.7804. Min Act: -0.0001

Data Index: 1512369 (Python Code)

Max Activating Token Index: 45

Text #7

Max Range: 0.8518. Min Range: -0.8518

Max Act: 0.7452. Min Act: -0.0001

Data Index: 1391445 (Python Code)

Max Activating Token Index: 673

Text #8

Max Range: 0.8518. Min Range: -0.8518

Max Act: 0.7487. Min Act: -0.0001

Data Index: 1649602 (Python Code)

Max Activating Token Index: 57

Text #9

Max Range: 0.8518. Min Range: -0.8518

Max Act: 0.7335. Min Act: -0.0001

Data Index: 1442061 (Python Code)

Max Activating Token Index: 42

Text #10

Max Range: 0.8518. Min Range: -0.8518

Max Act: 0.6896. Min Act: -0.0001

Data Index: 1517381 (Python Code)

Max Activating Token Index: 885

Text #11

Max Range: 0.8518. Min Range: -0.8518

Max Act: 0.7644. Min Act: -0.0001

Data Index: 1424953 (Python Code)

Max Activating Token Index: 796

Text #12

Max Range: 0.8518. Min Range: -0.8518

Max Act: 0.7565. Min Act: -0.0001

Data Index: 353201 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 0.8518. Min Range: -0.8518

Max Act: 0.6843. Min Act: -0.0001

Data Index: 1636998 (Python Code)

Max Activating Token Index: 65

Text #14

Max Range: 0.8518. Min Range: -0.8518

Max Act: 0.6783. Min Act: -0.0001

Data Index: 1623749 (Python Code)

Max Activating Token Index: 436

Text #15

Max Range: 0.8518. Min Range: -0.8518

Max Act: 0.6774. Min Act: -0.0001

Data Index: 1419377 (Python Code)

Max Activating Token Index: 24

Text #16

Max Range: 0.8518. Min Range: -0.8518

Max Act: 0.7135. Min Act: -0.0001

Data Index: 1503205 (Python Code)

Max Activating Token Index: 624

Text #17

Max Range: 0.8518. Min Range: -0.8518

Max Act: 0.7033. Min Act: -0.0001

Data Index: 464146 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 0.8518. Min Range: -0.8518

Max Act: 0.7209. Min Act: -0.0001

Data Index: 1508211 (Python Code)

Max Activating Token Index: 816

Text #19

Max Range: 0.8518. Min Range: -0.8518

Max Act: 0.6912. Min Act: -0.0001

Data Index: 1511579 (Python Code)

Max Activating Token Index: 626