Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3647 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1572. Min Range: -1.1572

Max Act: 1.1307. Min Act: -0.0001

Data Index: 1628688 (Python Code)

Max Activating Token Index: 661

Text #1

Max Range: 1.1572. Min Range: -1.1572

Max Act: 1.1290. Min Act: -0.0000

Data Index: 1439690 (Python Code)

Max Activating Token Index: 188

Text #2

Max Range: 1.1572. Min Range: -1.1572

Max Act: 1.1572. Min Act: -0.0000

Data Index: 1617051 (Python Code)

Max Activating Token Index: 836

Text #3

Max Range: 1.1572. Min Range: -1.1572

Max Act: 1.0548. Min Act: -0.0000

Data Index: 1412474 (Python Code)

Max Activating Token Index: 415

Text #4

Max Range: 1.1572. Min Range: -1.1572

Max Act: 1.0854. Min Act: -0.0000

Data Index: 1467563 (Python Code)

Max Activating Token Index: 110

Text #5

Max Range: 1.1572. Min Range: -1.1572

Max Act: 1.0746. Min Act: -0.0000

Data Index: 1640525 (Python Code)

Max Activating Token Index: 163

Text #6

Max Range: 1.1572. Min Range: -1.1572

Max Act: 1.0690. Min Act: -0.0001

Data Index: 1530810 (Python Code)

Max Activating Token Index: 52

Text #7

Max Range: 1.1572. Min Range: -1.1572

Max Act: 0.9952. Min Act: -0.0000

Data Index: 1650125 (Python Code)

Max Activating Token Index: 326

Text #8

Max Range: 1.1572. Min Range: -1.1572

Max Act: 1.0504. Min Act: -0.0001

Data Index: 1472626 (Python Code)

Max Activating Token Index: 19

Text #9

Max Range: 1.1572. Min Range: -1.1572

Max Act: 1.0738. Min Act: -0.0001

Data Index: 1533870 (Python Code)

Max Activating Token Index: 760

Text #10

Max Range: 1.1572. Min Range: -1.1572

Max Act: 1.0386. Min Act: -0.0000

Data Index: 1509357 (Python Code)

Max Activating Token Index: 179

Text #11

Max Range: 1.1572. Min Range: -1.1572

Max Act: 0.9642. Min Act: -0.0000

Data Index: 1515363 (Python Code)

Max Activating Token Index: 579

Text #12

Max Range: 1.1572. Min Range: -1.1572

Max Act: 1.0314. Min Act: -0.0000

Data Index: 1604397 (Python Code)

Max Activating Token Index: 749

Text #13

Max Range: 1.1572. Min Range: -1.1572

Max Act: 1.0222. Min Act: -0.0000

Data Index: 1449697 (Python Code)

Max Activating Token Index: 382

Text #14

Max Range: 1.1572. Min Range: -1.1572

Max Act: 1.0185. Min Act: -0.0000

Data Index: 1504959 (Python Code)

Max Activating Token Index: 47

Text #15

Max Range: 1.1572. Min Range: -1.1572

Max Act: 0.9793. Min Act: -0.0000

Data Index: 1536393 (Python Code)

Max Activating Token Index: 993

Text #16

Max Range: 1.1572. Min Range: -1.1572

Max Act: 0.9744. Min Act: -0.0001

Data Index: 1460657 (Python Code)

Max Activating Token Index: 548

Text #17

Max Range: 1.1572. Min Range: -1.1572

Max Act: 0.9079. Min Act: -0.0000

Data Index: 1593071 (Python Code)

Max Activating Token Index: 657

Text #18

Max Range: 1.1572. Min Range: -1.1572

Max Act: 0.9766. Min Act: -0.0001

Data Index: 1547151 (Python Code)

Max Activating Token Index: 241

Text #19

Max Range: 1.1572. Min Range: -1.1572

Max Act: 0.9423. Min Act: -0.0000

Data Index: 1652845 (Python Code)

Max Activating Token Index: 362