Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6034 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7676. Min Range: -1.7676

Max Act: 1.7676. Min Act: -0.0000

Data Index: 1591338 (Python Code)

Max Activating Token Index: 136

Text #1

Max Range: 1.7676. Min Range: -1.7676

Max Act: 1.4061. Min Act: -0.0000

Data Index: 1539751 (Python Code)

Max Activating Token Index: 186

Text #2

Max Range: 1.7676. Min Range: -1.7676

Max Act: 1.4597. Min Act: -0.0000

Data Index: 942717 (C4 (Web Text))

Max Activating Token Index: 134

Text #3

Max Range: 1.7676. Min Range: -1.7676

Max Act: 1.4162. Min Act: -0.0000

Data Index: 855727 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 1.7676. Min Range: -1.7676

Max Act: 1.4118. Min Act: -0.0000

Data Index: 1503909 (Python Code)

Max Activating Token Index: 449

Text #5

Max Range: 1.7676. Min Range: -1.7676

Max Act: 1.3292. Min Act: 0.0000

Data Index: 743216 (C4 (Web Text))

Max Activating Token Index: 580

Text #6

Max Range: 1.7676. Min Range: -1.7676

Max Act: 1.2478. Min Act: -0.0000

Data Index: 1007095 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 1.7676. Min Range: -1.7676

Max Act: 1.1936. Min Act: -0.0000

Data Index: 1616337 (Python Code)

Max Activating Token Index: 447

Text #8

Max Range: 1.7676. Min Range: -1.7676

Max Act: 1.2641. Min Act: -0.0000

Data Index: 1599336 (Python Code)

Max Activating Token Index: 673

Text #9

Max Range: 1.7676. Min Range: -1.7676

Max Act: 1.3330. Min Act: -0.0000

Data Index: 1641068 (Python Code)

Max Activating Token Index: 612

Text #10

Max Range: 1.7676. Min Range: -1.7676

Max Act: 1.2608. Min Act: 0.0000

Data Index: 445126 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 1.7676. Min Range: -1.7676

Max Act: 1.2381. Min Act: -0.0000

Data Index: 1277812 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 1.7676. Min Range: -1.7676

Max Act: 1.1615. Min Act: -0.0000

Data Index: 1498930 (Python Code)

Max Activating Token Index: 296

Text #13

Max Range: 1.7676. Min Range: -1.7676

Max Act: 1.2349. Min Act: -0.0000

Data Index: 1470336 (Python Code)

Max Activating Token Index: 204

Text #14

Max Range: 1.7676. Min Range: -1.7676

Max Act: 1.2230. Min Act: -0.0000

Data Index: 1552528 (Python Code)

Max Activating Token Index: 950

Text #15

Max Range: 1.7676. Min Range: -1.7676

Max Act: 1.1985. Min Act: -0.0000

Data Index: 1553401 (Python Code)

Max Activating Token Index: 493

Text #16

Max Range: 1.7676. Min Range: -1.7676

Max Act: 1.2737. Min Act: -0.0000

Data Index: 1442478 (Python Code)

Max Activating Token Index: 940

Text #17

Max Range: 1.7676. Min Range: -1.7676

Max Act: 1.1831. Min Act: 0.0001

Data Index: 1593945 (Python Code)

Max Activating Token Index: 194

Text #18

Max Range: 1.7676. Min Range: -1.7676

Max Act: 1.1616. Min Act: -0.0000

Data Index: 1384096 (Python Code)

Max Activating Token Index: 60

Text #19

Max Range: 1.7676. Min Range: -1.7676

Max Act: 1.1590. Min Act: -0.0000

Data Index: 1652196 (Python Code)

Max Activating Token Index: 420