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

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

Neuron 1330 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: 3.6751. Min Range: -3.6751

Max Act: 3.4482. Min Act: -0.0000

Data Index: 1640658 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 3.6751. Min Range: -3.6751

Max Act: 3.6751. Min Act: -0.0000

Data Index: 1596533 (Python Code)

Max Activating Token Index: 894

Text #2

Max Range: 3.6751. Min Range: -3.6751

Max Act: 3.2395. Min Act: -0.0000

Data Index: 1406035 (Python Code)

Max Activating Token Index: 122

Text #3

Max Range: 3.6751. Min Range: -3.6751

Max Act: 2.6101. Min Act: -0.0000

Data Index: 1480500 (Python Code)

Max Activating Token Index: 277

Text #4

Max Range: 3.6751. Min Range: -3.6751

Max Act: 2.5986. Min Act: -0.0000

Data Index: 1519297 (Python Code)

Max Activating Token Index: 564

Text #5

Max Range: 3.6751. Min Range: -3.6751

Max Act: 2.4587. Min Act: -0.0000

Data Index: 1619524 (Python Code)

Max Activating Token Index: 230

Text #6

Max Range: 3.6751. Min Range: -3.6751

Max Act: 2.5653. Min Act: -0.0000

Data Index: 1378238 (Python Code)

Max Activating Token Index: 810

Text #7

Max Range: 3.6751. Min Range: -3.6751

Max Act: 2.1802. Min Act: -0.0000

Data Index: 1452518 (Python Code)

Max Activating Token Index: 651

Text #8

Max Range: 3.6751. Min Range: -3.6751

Max Act: 2.2996. Min Act: -0.0000

Data Index: 1541461 (Python Code)

Max Activating Token Index: 102

Text #9

Max Range: 3.6751. Min Range: -3.6751

Max Act: 2.2039. Min Act: -0.0000

Data Index: 1524031 (Python Code)

Max Activating Token Index: 661

Text #10

Max Range: 3.6751. Min Range: -3.6751

Max Act: 2.0287. Min Act: -0.0000

Data Index: 1445397 (Python Code)

Max Activating Token Index: 441

Text #11

Max Range: 3.6751. Min Range: -3.6751

Max Act: 2.2523. Min Act: -0.0000

Data Index: 1458445 (Python Code)

Max Activating Token Index: 832

Text #12

Max Range: 3.6751. Min Range: -3.6751

Max Act: 1.8962. Min Act: -0.0000

Data Index: 1457995 (Python Code)

Max Activating Token Index: 530

Text #13

Max Range: 3.6751. Min Range: -3.6751

Max Act: 1.8944. Min Act: -0.0000

Data Index: 1437107 (Python Code)

Max Activating Token Index: 945

Text #14

Max Range: 3.6751. Min Range: -3.6751

Max Act: 1.8474. Min Act: -0.0000

Data Index: 1566115 (Python Code)

Max Activating Token Index: 608

Text #15

Max Range: 3.6751. Min Range: -3.6751

Max Act: 1.8376. Min Act: -0.0000

Data Index: 1461834 (Python Code)

Max Activating Token Index: 174

Text #16

Max Range: 3.6751. Min Range: -3.6751

Max Act: 1.8965. Min Act: -0.0000

Data Index: 1499313 (Python Code)

Max Activating Token Index: 858

Text #17

Max Range: 3.6751. Min Range: -3.6751

Max Act: 1.6953. Min Act: -0.0000

Data Index: 1573525 (Python Code)

Max Activating Token Index: 326

Text #18

Max Range: 3.6751. Min Range: -3.6751

Max Act: 1.6867. Min Act: -0.0000

Data Index: 1597269 (Python Code)

Max Activating Token Index: 402

Text #19

Max Range: 3.6751. Min Range: -3.6751

Max Act: 1.6884. Min Act: -0.0000

Data Index: 1407806 (Python Code)

Max Activating Token Index: 981