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

Dataset: The Pile

Neuron 1415 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.6994. Min Act: -0.0000

Data Index: 1727194 (The Pile)

Max Activating Token Index: 402

Text #1

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.6881. Min Act: -0.0000

Data Index: 266433 (The Pile)

Max Activating Token Index: 960

Text #2

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5817. Min Act: -0.0000

Data Index: 1626194 (The Pile)

Max Activating Token Index: 624

Text #3

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5047. Min Act: -0.0000

Data Index: 1750128 (The Pile)

Max Activating Token Index: 503

Text #4

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4508. Min Act: -0.0000

Data Index: 903978 (The Pile)

Max Activating Token Index: 882

Text #5

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4308. Min Act: -0.0000

Data Index: 1149244 (The Pile)

Max Activating Token Index: 271

Text #6

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4804. Min Act: -0.0000

Data Index: 1710480 (The Pile)

Max Activating Token Index: 207

Text #7

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4102. Min Act: -0.0000

Data Index: 355147 (The Pile)

Max Activating Token Index: 727

Text #8

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.3736. Min Act: -0.0000

Data Index: 1311737 (The Pile)

Max Activating Token Index: 956

Text #9

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.3767. Min Act: -0.0000

Data Index: 626566 (The Pile)

Max Activating Token Index: 251

Text #10

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.3975. Min Act: -0.0000

Data Index: 606498 (The Pile)

Max Activating Token Index: 425

Text #11

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.3893. Min Act: -0.0000

Data Index: 1575860 (The Pile)

Max Activating Token Index: 679

Text #12

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.3356. Min Act: -0.0000

Data Index: 282654 (The Pile)

Max Activating Token Index: 570

Text #13

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.3640. Min Act: -0.0000

Data Index: 1346335 (The Pile)

Max Activating Token Index: 941

Text #14

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.3546. Min Act: -0.0000

Data Index: 1739850 (The Pile)

Max Activating Token Index: 630

Text #15

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.3573. Min Act: -0.0000

Data Index: 1858950 (The Pile)

Max Activating Token Index: 399

Text #16

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.3571. Min Act: -0.0000

Data Index: 1198152 (The Pile)

Max Activating Token Index: 521

Text #17

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.3495. Min Act: -0.0000

Data Index: 291208 (The Pile)

Max Activating Token Index: 457

Text #18

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.3681. Min Act: -0.0000

Data Index: 1066314 (The Pile)

Max Activating Token Index: 689

Text #19

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4129. Min Act: -0.0000

Data Index: 930551 (The Pile)

Max Activating Token Index: 1003