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

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

Neuron 5429 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: 2.3424. Min Range: -2.3424

Max Act: 2.1899. Min Act: -0.0000

Data Index: 1514265 (Python Code)

Max Activating Token Index: 847

Text #1

Max Range: 2.3424. Min Range: -2.3424

Max Act: 2.2913. Min Act: -0.0000

Data Index: 1464539 (Python Code)

Max Activating Token Index: 764

Text #2

Max Range: 2.3424. Min Range: -2.3424

Max Act: 2.1320. Min Act: -0.0000

Data Index: 1441250 (Python Code)

Max Activating Token Index: 445

Text #3

Max Range: 2.3424. Min Range: -2.3424

Max Act: 2.3424. Min Act: -0.0000

Data Index: 1475061 (Python Code)

Max Activating Token Index: 923

Text #4

Max Range: 2.3424. Min Range: -2.3424

Max Act: 1.9618. Min Act: -0.0000

Data Index: 1505573 (Python Code)

Max Activating Token Index: 414

Text #5

Max Range: 2.3424. Min Range: -2.3424

Max Act: 2.1805. Min Act: -0.0000

Data Index: 1620202 (Python Code)

Max Activating Token Index: 359

Text #6

Max Range: 2.3424. Min Range: -2.3424

Max Act: 2.1783. Min Act: -0.0000

Data Index: 1572102 (Python Code)

Max Activating Token Index: 449

Text #7

Max Range: 2.3424. Min Range: -2.3424

Max Act: 2.0294. Min Act: -0.0000

Data Index: 1478352 (Python Code)

Max Activating Token Index: 370

Text #8

Max Range: 2.3424. Min Range: -2.3424

Max Act: 2.0777. Min Act: -0.0000

Data Index: 1645336 (Python Code)

Max Activating Token Index: 598

Text #9

Max Range: 2.3424. Min Range: -2.3424

Max Act: 1.9689. Min Act: -0.0000

Data Index: 1539083 (Python Code)

Max Activating Token Index: 729

Text #10

Max Range: 2.3424. Min Range: -2.3424

Max Act: 2.0568. Min Act: -0.0000

Data Index: 1453749 (Python Code)

Max Activating Token Index: 606

Text #11

Max Range: 2.3424. Min Range: -2.3424

Max Act: 1.8311. Min Act: -0.0000

Data Index: 1542795 (Python Code)

Max Activating Token Index: 810

Text #12

Max Range: 2.3424. Min Range: -2.3424

Max Act: 1.9265. Min Act: -0.0000

Data Index: 1378802 (Python Code)

Max Activating Token Index: 159

Text #13

Max Range: 2.3424. Min Range: -2.3424

Max Act: 1.7233. Min Act: -0.0000

Data Index: 1603649 (Python Code)

Max Activating Token Index: 737

Text #14

Max Range: 2.3424. Min Range: -2.3424

Max Act: 1.9020. Min Act: -0.0000

Data Index: 1654528 (Python Code)

Max Activating Token Index: 249

Text #15

Max Range: 2.3424. Min Range: -2.3424

Max Act: 1.9115. Min Act: -0.0000

Data Index: 1572242 (Python Code)

Max Activating Token Index: 25

Text #16

Max Range: 2.3424. Min Range: -2.3424

Max Act: 2.0135. Min Act: -0.0000

Data Index: 1634429 (Python Code)

Max Activating Token Index: 189

Text #17

Max Range: 2.3424. Min Range: -2.3424

Max Act: 1.8842. Min Act: -0.0000

Data Index: 1368999 (Python Code)

Max Activating Token Index: 279

Text #18

Max Range: 2.3424. Min Range: -2.3424

Max Act: 1.8903. Min Act: -0.0000

Data Index: 1400058 (Python Code)

Max Activating Token Index: 759

Text #19

Max Range: 2.3424. Min Range: -2.3424

Max Act: 1.9741. Min Act: -0.0000

Data Index: 1461508 (Python Code)

Max Activating Token Index: 204