Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3847 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.3591. Min Act: -0.0000

Data Index: 1911689 (The Pile)

Max Activating Token Index: 350

Text #1

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.3958. Min Act: -0.0000

Data Index: 728440 (The Pile)

Max Activating Token Index: 104

Text #2

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.3226. Min Act: -0.0000

Data Index: 1278180 (The Pile)

Max Activating Token Index: 590

Text #3

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.2938. Min Act: -0.0000

Data Index: 1902308 (The Pile)

Max Activating Token Index: 126

Text #4

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.2984. Min Act: -0.0000

Data Index: 1788866 (The Pile)

Max Activating Token Index: 550

Text #5

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.3104. Min Act: -0.0000

Data Index: 1203548 (The Pile)

Max Activating Token Index: 371

Text #6

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.2995. Min Act: -0.0000

Data Index: 1173452 (The Pile)

Max Activating Token Index: 428

Text #7

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.2672. Min Act: -0.0000

Data Index: 961021 (The Pile)

Max Activating Token Index: 886

Text #8

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.2803. Min Act: -0.0000

Data Index: 1015428 (The Pile)

Max Activating Token Index: 28

Text #9

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.2906. Min Act: -0.0000

Data Index: 771205 (The Pile)

Max Activating Token Index: 626

Text #10

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.2393. Min Act: -0.0000

Data Index: 887627 (The Pile)

Max Activating Token Index: 991

Text #11

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.2745. Min Act: -0.0000

Data Index: 23280 (The Pile)

Max Activating Token Index: 12

Text #12

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.2648. Min Act: -0.0000

Data Index: 1530903 (The Pile)

Max Activating Token Index: 435

Text #13

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.2833. Min Act: -0.0000

Data Index: 1442043 (The Pile)

Max Activating Token Index: 918

Text #14

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.2451. Min Act: -0.0000

Data Index: 951821 (The Pile)

Max Activating Token Index: 993

Text #15

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.2574. Min Act: -0.0000

Data Index: 1425701 (The Pile)

Max Activating Token Index: 13

Text #16

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.2420. Min Act: -0.0000

Data Index: 1385248 (The Pile)

Max Activating Token Index: 446

Text #17

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.2560. Min Act: -0.0000

Data Index: 1501594 (The Pile)

Max Activating Token Index: 711

Text #18

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.2495. Min Act: -0.0000

Data Index: 1932592 (The Pile)

Max Activating Token Index: 13

Text #19

Max Range: 0.3958. Min Range: -0.3958

Max Act: 0.2381. Min Act: -0.0000

Data Index: 132342 (The Pile)

Max Activating Token Index: 831