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

Dataset: The Pile

Neuron 3825 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2790. Min Range: -3.2790

Max Act: 3.1360. Min Act: -0.0000

Data Index: 1433820 (The Pile)

Max Activating Token Index: 870

Text #1

Max Range: 3.2790. Min Range: -3.2790

Max Act: 3.2790. Min Act: -0.0000

Data Index: 1815671 (The Pile)

Max Activating Token Index: 447

Text #2

Max Range: 3.2790. Min Range: -3.2790

Max Act: 3.2057. Min Act: -0.0000

Data Index: 1026390 (The Pile)

Max Activating Token Index: 57

Text #3

Max Range: 3.2790. Min Range: -3.2790

Max Act: 3.1756. Min Act: -0.0000

Data Index: 980805 (The Pile)

Max Activating Token Index: 221

Text #4

Max Range: 3.2790. Min Range: -3.2790

Max Act: 3.2759. Min Act: -0.0000

Data Index: 1374546 (The Pile)

Max Activating Token Index: 950

Text #5

Max Range: 3.2790. Min Range: -3.2790

Max Act: 3.2025. Min Act: -0.0000

Data Index: 1361007 (The Pile)

Max Activating Token Index: 1022

Text #6

Max Range: 3.2790. Min Range: -3.2790

Max Act: 3.0422. Min Act: -0.0000

Data Index: 559073 (The Pile)

Max Activating Token Index: 683

Text #7

Max Range: 3.2790. Min Range: -3.2790

Max Act: 2.9963. Min Act: -0.0000

Data Index: 1103826 (The Pile)

Max Activating Token Index: 838

Text #8

Max Range: 3.2790. Min Range: -3.2790

Max Act: 2.5493. Min Act: -0.0000

Data Index: 1155219 (The Pile)

Max Activating Token Index: 963

Text #9

Max Range: 3.2790. Min Range: -3.2790

Max Act: 2.9531. Min Act: -0.0000

Data Index: 981432 (The Pile)

Max Activating Token Index: 64

Text #10

Max Range: 3.2790. Min Range: -3.2790

Max Act: 2.8375. Min Act: -0.0000

Data Index: 1117893 (The Pile)

Max Activating Token Index: 139

Text #11

Max Range: 3.2790. Min Range: -3.2790

Max Act: 2.8552. Min Act: -0.0000

Data Index: 1425171 (The Pile)

Max Activating Token Index: 436

Text #12

Max Range: 3.2790. Min Range: -3.2790

Max Act: 2.9507. Min Act: -0.0000

Data Index: 593559 (The Pile)

Max Activating Token Index: 970

Text #13

Max Range: 3.2790. Min Range: -3.2790

Max Act: 3.0877. Min Act: -0.0000

Data Index: 1669678 (The Pile)

Max Activating Token Index: 459

Text #14

Max Range: 3.2790. Min Range: -3.2790

Max Act: 3.1022. Min Act: -0.0000

Data Index: 1947672 (The Pile)

Max Activating Token Index: 543

Text #15

Max Range: 3.2790. Min Range: -3.2790

Max Act: 2.6601. Min Act: -0.0000

Data Index: 858118 (The Pile)

Max Activating Token Index: 834

Text #16

Max Range: 3.2790. Min Range: -3.2790

Max Act: 2.8976. Min Act: -0.0000

Data Index: 1849892 (The Pile)

Max Activating Token Index: 421

Text #17

Max Range: 3.2790. Min Range: -3.2790

Max Act: 2.7470. Min Act: -0.0000

Data Index: 418999 (The Pile)

Max Activating Token Index: 271

Text #18

Max Range: 3.2790. Min Range: -3.2790

Max Act: 2.8729. Min Act: -0.0000

Data Index: 1465718 (The Pile)

Max Activating Token Index: 855

Text #19

Max Range: 3.2790. Min Range: -3.2790

Max Act: 2.8696. Min Act: -0.0000

Data Index: 513809 (The Pile)

Max Activating Token Index: 946