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

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

Neuron 5303 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3556. Min Range: -5.3556

Max Act: 5.2112. Min Act: -0.0000

Data Index: 1500101 (Python Code)

Max Activating Token Index: 278

Text #1

Max Range: 5.3556. Min Range: -5.3556

Max Act: 5.3556. Min Act: -0.0000

Data Index: 1417074 (Python Code)

Max Activating Token Index: 275

Text #2

Max Range: 5.3556. Min Range: -5.3556

Max Act: 5.2016. Min Act: -0.0000

Data Index: 1380155 (Python Code)

Max Activating Token Index: 189

Text #3

Max Range: 5.3556. Min Range: -5.3556

Max Act: 5.1755. Min Act: -0.0000

Data Index: 1471767 (Python Code)

Max Activating Token Index: 968

Text #4

Max Range: 5.3556. Min Range: -5.3556

Max Act: 5.1441. Min Act: -0.0000

Data Index: 1442638 (Python Code)

Max Activating Token Index: 289

Text #5

Max Range: 5.3556. Min Range: -5.3556

Max Act: 4.9035. Min Act: -0.0000

Data Index: 1564694 (Python Code)

Max Activating Token Index: 624

Text #6

Max Range: 5.3556. Min Range: -5.3556

Max Act: 5.0705. Min Act: -0.0000

Data Index: 1514776 (Python Code)

Max Activating Token Index: 906

Text #7

Max Range: 5.3556. Min Range: -5.3556

Max Act: 5.0618. Min Act: -0.0000

Data Index: 1533305 (Python Code)

Max Activating Token Index: 962

Text #8

Max Range: 5.3556. Min Range: -5.3556

Max Act: 5.0333. Min Act: -0.0000

Data Index: 1577197 (Python Code)

Max Activating Token Index: 916

Text #9

Max Range: 5.3556. Min Range: -5.3556

Max Act: 4.6755. Min Act: -0.0000

Data Index: 1564059 (Python Code)

Max Activating Token Index: 157

Text #10

Max Range: 5.3556. Min Range: -5.3556

Max Act: 4.8300. Min Act: -0.0000

Data Index: 1514183 (Python Code)

Max Activating Token Index: 93

Text #11

Max Range: 5.3556. Min Range: -5.3556

Max Act: 4.8176. Min Act: -0.0000

Data Index: 1446596 (Python Code)

Max Activating Token Index: 439

Text #12

Max Range: 5.3556. Min Range: -5.3556

Max Act: 4.6660. Min Act: -0.0000

Data Index: 1638394 (Python Code)

Max Activating Token Index: 773

Text #13

Max Range: 5.3556. Min Range: -5.3556

Max Act: 4.7723. Min Act: -0.0000

Data Index: 1580665 (Python Code)

Max Activating Token Index: 887

Text #14

Max Range: 5.3556. Min Range: -5.3556

Max Act: 4.8181. Min Act: -0.0000

Data Index: 1516349 (Python Code)

Max Activating Token Index: 812

Text #15

Max Range: 5.3556. Min Range: -5.3556

Max Act: 4.7355. Min Act: -0.0000

Data Index: 1508674 (Python Code)

Max Activating Token Index: 455

Text #16

Max Range: 5.3556. Min Range: -5.3556

Max Act: 4.8868. Min Act: -0.0000

Data Index: 1494298 (Python Code)

Max Activating Token Index: 702

Text #17

Max Range: 5.3556. Min Range: -5.3556

Max Act: 4.7287. Min Act: -0.0000

Data Index: 1456825 (Python Code)

Max Activating Token Index: 872

Text #18

Max Range: 5.3556. Min Range: -5.3556

Max Act: 4.7152. Min Act: -0.0000

Data Index: 1555158 (Python Code)

Max Activating Token Index: 137

Text #19

Max Range: 5.3556. Min Range: -5.3556

Max Act: 4.7058. Min Act: -0.0000

Data Index: 1498502 (Python Code)

Max Activating Token Index: 261