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

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

Neuron 1584 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5553. Min Range: -3.5553

Max Act: 3.3747. Min Act: -0.0000

Data Index: 1389245 (Python Code)

Max Activating Token Index: 359

Text #1

Max Range: 3.5553. Min Range: -3.5553

Max Act: 3.5553. Min Act: -0.0000

Data Index: 1406192 (Python Code)

Max Activating Token Index: 733

Text #2

Max Range: 3.5553. Min Range: -3.5553

Max Act: 2.9242. Min Act: -0.0000

Data Index: 1384729 (Python Code)

Max Activating Token Index: 235

Text #3

Max Range: 3.5553. Min Range: -3.5553

Max Act: 2.8528. Min Act: -0.0000

Data Index: 1409708 (Python Code)

Max Activating Token Index: 530

Text #4

Max Range: 3.5553. Min Range: -3.5553

Max Act: 2.4854. Min Act: -0.0000

Data Index: 1455195 (Python Code)

Max Activating Token Index: 295

Text #5

Max Range: 3.5553. Min Range: -3.5553

Max Act: 2.5045. Min Act: -0.0000

Data Index: 1637420 (Python Code)

Max Activating Token Index: 644

Text #6

Max Range: 3.5553. Min Range: -3.5553

Max Act: 2.2429. Min Act: -0.0000

Data Index: 1602119 (Python Code)

Max Activating Token Index: 367

Text #7

Max Range: 3.5553. Min Range: -3.5553

Max Act: 2.2885. Min Act: -0.0000

Data Index: 1544844 (Python Code)

Max Activating Token Index: 216

Text #8

Max Range: 3.5553. Min Range: -3.5553

Max Act: 2.1727. Min Act: -0.0000

Data Index: 1585132 (Python Code)

Max Activating Token Index: 785

Text #9

Max Range: 3.5553. Min Range: -3.5553

Max Act: 1.9932. Min Act: -0.0000

Data Index: 1531686 (Python Code)

Max Activating Token Index: 827

Text #10

Max Range: 3.5553. Min Range: -3.5553

Max Act: 2.0869. Min Act: -0.0000

Data Index: 1427569 (Python Code)

Max Activating Token Index: 723

Text #11

Max Range: 3.5553. Min Range: -3.5553

Max Act: 2.0865. Min Act: -0.0000

Data Index: 1408168 (Python Code)

Max Activating Token Index: 622

Text #12

Max Range: 3.5553. Min Range: -3.5553

Max Act: 2.1388. Min Act: -0.0000

Data Index: 1632230 (Python Code)

Max Activating Token Index: 813

Text #13

Max Range: 3.5553. Min Range: -3.5553

Max Act: 2.0700. Min Act: -0.0000

Data Index: 1609792 (Python Code)

Max Activating Token Index: 186

Text #14

Max Range: 3.5553. Min Range: -3.5553

Max Act: 2.1819. Min Act: -0.0000

Data Index: 1440578 (Python Code)

Max Activating Token Index: 490

Text #15

Max Range: 3.5553. Min Range: -3.5553

Max Act: 2.2321. Min Act: -0.0000

Data Index: 1614159 (Python Code)

Max Activating Token Index: 900

Text #16

Max Range: 3.5553. Min Range: -3.5553

Max Act: 2.1841. Min Act: -0.0000

Data Index: 1501038 (Python Code)

Max Activating Token Index: 871

Text #17

Max Range: 3.5553. Min Range: -3.5553

Max Act: 2.0615. Min Act: -0.0000

Data Index: 1581797 (Python Code)

Max Activating Token Index: 657

Text #18

Max Range: 3.5553. Min Range: -3.5553

Max Act: 2.1619. Min Act: -0.0000

Data Index: 1463685 (Python Code)

Max Activating Token Index: 486

Text #19

Max Range: 3.5553. Min Range: -3.5553

Max Act: 2.1082. Min Act: -0.0000

Data Index: 1524715 (Python Code)

Max Activating Token Index: 468