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

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

Neuron 4384 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6687. Min Range: -2.6687

Max Act: 2.6548. Min Act: -0.0000

Data Index: 1450736 (Python Code)

Max Activating Token Index: 966

Text #1

Max Range: 2.6687. Min Range: -2.6687

Max Act: 2.6687. Min Act: -0.0000

Data Index: 1477503 (Python Code)

Max Activating Token Index: 501

Text #2

Max Range: 2.6687. Min Range: -2.6687

Max Act: 2.1012. Min Act: -0.0000

Data Index: 1387198 (Python Code)

Max Activating Token Index: 586

Text #3

Max Range: 2.6687. Min Range: -2.6687

Max Act: 2.0884. Min Act: -0.0000

Data Index: 1606215 (Python Code)

Max Activating Token Index: 736

Text #4

Max Range: 2.6687. Min Range: -2.6687

Max Act: 1.8747. Min Act: -0.0000

Data Index: 1369365 (Python Code)

Max Activating Token Index: 183

Text #5

Max Range: 2.6687. Min Range: -2.6687

Max Act: 1.8323. Min Act: -0.0000

Data Index: 1369910 (Python Code)

Max Activating Token Index: 221

Text #6

Max Range: 2.6687. Min Range: -2.6687

Max Act: 1.8470. Min Act: -0.0000

Data Index: 1541243 (Python Code)

Max Activating Token Index: 283

Text #7

Max Range: 2.6687. Min Range: -2.6687

Max Act: 1.7906. Min Act: -0.0000

Data Index: 1643394 (Python Code)

Max Activating Token Index: 562

Text #8

Max Range: 2.6687. Min Range: -2.6687

Max Act: 1.6416. Min Act: -0.0000

Data Index: 1544221 (Python Code)

Max Activating Token Index: 444

Text #9

Max Range: 2.6687. Min Range: -2.6687

Max Act: 1.4566. Min Act: -0.0000

Data Index: 1562952 (Python Code)

Max Activating Token Index: 70

Text #10

Max Range: 2.6687. Min Range: -2.6687

Max Act: 1.5251. Min Act: -0.0000

Data Index: 1627755 (Python Code)

Max Activating Token Index: 30

Text #11

Max Range: 2.6687. Min Range: -2.6687

Max Act: 1.4808. Min Act: -0.0000

Data Index: 1394823 (Python Code)

Max Activating Token Index: 988

Text #12

Max Range: 2.6687. Min Range: -2.6687

Max Act: 1.5288. Min Act: -0.0000

Data Index: 1577895 (Python Code)

Max Activating Token Index: 972

Text #13

Max Range: 2.6687. Min Range: -2.6687

Max Act: 1.4331. Min Act: -0.0000

Data Index: 1373273 (Python Code)

Max Activating Token Index: 212

Text #14

Max Range: 2.6687. Min Range: -2.6687

Max Act: 1.4166. Min Act: -0.0000

Data Index: 1483106 (Python Code)

Max Activating Token Index: 606

Text #15

Max Range: 2.6687. Min Range: -2.6687

Max Act: 1.3261. Min Act: -0.0000

Data Index: 1564186 (Python Code)

Max Activating Token Index: 500

Text #16

Max Range: 2.6687. Min Range: -2.6687

Max Act: 1.3134. Min Act: -0.0000

Data Index: 1537264 (Python Code)

Max Activating Token Index: 589

Text #17

Max Range: 2.6687. Min Range: -2.6687

Max Act: 1.2905. Min Act: -0.0000

Data Index: 1550786 (Python Code)

Max Activating Token Index: 806

Text #18

Max Range: 2.6687. Min Range: -2.6687

Max Act: 1.3700. Min Act: -0.0000

Data Index: 1396370 (Python Code)

Max Activating Token Index: 452

Text #19

Max Range: 2.6687. Min Range: -2.6687

Max Act: 1.3618. Min Act: -0.0000

Data Index: 1573802 (Python Code)

Max Activating Token Index: 820