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

Dataset: The Pile

Neuron 3909 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: 0.0721. Min Range: -0.0721

Max Act: 0.0721. Min Act: -0.0000

Data Index: 1340082 (The Pile)

Max Activating Token Index: 908

Text #1

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0512. Min Act: -0.0000

Data Index: 1431432 (The Pile)

Max Activating Token Index: 810

Text #2

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0506. Min Act: -0.0000

Data Index: 397068 (The Pile)

Max Activating Token Index: 829

Text #3

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0495. Min Act: -0.0000

Data Index: 318280 (The Pile)

Max Activating Token Index: 964

Text #4

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0533. Min Act: -0.0000

Data Index: 1897073 (The Pile)

Max Activating Token Index: 964

Text #5

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0530. Min Act: -0.0000

Data Index: 937365 (The Pile)

Max Activating Token Index: 731

Text #6

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0523. Min Act: -0.0000

Data Index: 1544925 (The Pile)

Max Activating Token Index: 781

Text #7

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0484. Min Act: -0.0000

Data Index: 1155076 (The Pile)

Max Activating Token Index: 793

Text #8

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0494. Min Act: -0.0000

Data Index: 829173 (The Pile)

Max Activating Token Index: 746

Text #9

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0514. Min Act: -0.0000

Data Index: 911777 (The Pile)

Max Activating Token Index: 647

Text #10

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0468. Min Act: -0.0000

Data Index: 9457 (The Pile)

Max Activating Token Index: 308

Text #11

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0533. Min Act: -0.0000

Data Index: 922682 (The Pile)

Max Activating Token Index: 673

Text #12

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0454. Min Act: -0.0000

Data Index: 770981 (The Pile)

Max Activating Token Index: 1021

Text #13

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0453. Min Act: -0.0000

Data Index: 1825629 (The Pile)

Max Activating Token Index: 826

Text #14

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0535. Min Act: -0.0000

Data Index: 1363524 (The Pile)

Max Activating Token Index: 915

Text #15

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0413. Min Act: -0.0000

Data Index: 800640 (The Pile)

Max Activating Token Index: 897

Text #16

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0460. Min Act: -0.0000

Data Index: 1668862 (The Pile)

Max Activating Token Index: 416

Text #17

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0458. Min Act: -0.0000

Data Index: 763367 (The Pile)

Max Activating Token Index: 1018

Text #18

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0436. Min Act: -0.0000

Data Index: 592129 (The Pile)

Max Activating Token Index: 56

Text #19

Max Range: 0.0721. Min Range: -0.0721

Max Act: 0.0412. Min Act: -0.0000

Data Index: 204716 (The Pile)

Max Activating Token Index: 228