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

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

Neuron 5063 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: 4.4198. Min Range: -4.4198

Max Act: 4.4198. Min Act: -0.0000

Data Index: 1463480 (Python Code)

Max Activating Token Index: 752

Text #1

Max Range: 4.4198. Min Range: -4.4198

Max Act: 3.8158. Min Act: -0.0000

Data Index: 1570041 (Python Code)

Max Activating Token Index: 421

Text #2

Max Range: 4.4198. Min Range: -4.4198

Max Act: 3.3927. Min Act: -0.0000

Data Index: 1612187 (Python Code)

Max Activating Token Index: 794

Text #3

Max Range: 4.4198. Min Range: -4.4198

Max Act: 3.3006. Min Act: -0.0000

Data Index: 1389672 (Python Code)

Max Activating Token Index: 718

Text #4

Max Range: 4.4198. Min Range: -4.4198

Max Act: 3.4204. Min Act: -0.0000

Data Index: 1603646 (Python Code)

Max Activating Token Index: 319

Text #5

Max Range: 4.4198. Min Range: -4.4198

Max Act: 3.2150. Min Act: -0.0000

Data Index: 1626961 (Python Code)

Max Activating Token Index: 538

Text #6

Max Range: 4.4198. Min Range: -4.4198

Max Act: 3.2044. Min Act: -0.0000

Data Index: 1426232 (Python Code)

Max Activating Token Index: 686

Text #7

Max Range: 4.4198. Min Range: -4.4198

Max Act: 3.1855. Min Act: -0.0000

Data Index: 1445909 (Python Code)

Max Activating Token Index: 261

Text #8

Max Range: 4.4198. Min Range: -4.4198

Max Act: 3.1839. Min Act: -0.0000

Data Index: 1423107 (Python Code)

Max Activating Token Index: 333

Text #9

Max Range: 4.4198. Min Range: -4.4198

Max Act: 3.0508. Min Act: -0.0000

Data Index: 1414397 (Python Code)

Max Activating Token Index: 308

Text #10

Max Range: 4.4198. Min Range: -4.4198

Max Act: 3.0126. Min Act: -0.0000

Data Index: 1384057 (Python Code)

Max Activating Token Index: 537

Text #11

Max Range: 4.4198. Min Range: -4.4198

Max Act: 3.1346. Min Act: -0.0000

Data Index: 1613561 (Python Code)

Max Activating Token Index: 696

Text #12

Max Range: 4.4198. Min Range: -4.4198

Max Act: 2.9831. Min Act: -0.0000

Data Index: 1561789 (Python Code)

Max Activating Token Index: 602

Text #13

Max Range: 4.4198. Min Range: -4.4198

Max Act: 2.9861. Min Act: -0.0000

Data Index: 1608877 (Python Code)

Max Activating Token Index: 963

Text #14

Max Range: 4.4198. Min Range: -4.4198

Max Act: 3.1154. Min Act: -0.0000

Data Index: 1639267 (Python Code)

Max Activating Token Index: 394

Text #15

Max Range: 4.4198. Min Range: -4.4198

Max Act: 2.9315. Min Act: -0.0000

Data Index: 1484665 (Python Code)

Max Activating Token Index: 90

Text #16

Max Range: 4.4198. Min Range: -4.4198

Max Act: 2.8653. Min Act: -0.0000

Data Index: 1620144 (Python Code)

Max Activating Token Index: 771

Text #17

Max Range: 4.4198. Min Range: -4.4198

Max Act: 2.8824. Min Act: -0.0000

Data Index: 1393810 (Python Code)

Max Activating Token Index: 34

Text #18

Max Range: 4.4198. Min Range: -4.4198

Max Act: 2.7343. Min Act: -0.0000

Data Index: 1522360 (Python Code)

Max Activating Token Index: 992

Text #19

Max Range: 4.4198. Min Range: -4.4198

Max Act: 3.0038. Min Act: -0.0000

Data Index: 1480991 (Python Code)

Max Activating Token Index: 110