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

Dataset: The Pile

Neuron 632 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: 0.0739. Min Range: -0.0739

Max Act: 0.0739. Min Act: -0.0000

Data Index: 491874 (The Pile)

Max Activating Token Index: 131

Text #1

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0616. Min Act: -0.0000

Data Index: 693581 (The Pile)

Max Activating Token Index: 726

Text #2

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0567. Min Act: -0.0000

Data Index: 1204292 (The Pile)

Max Activating Token Index: 535

Text #3

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0528. Min Act: -0.0000

Data Index: 1984689 (The Pile)

Max Activating Token Index: 884

Text #4

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0495. Min Act: -0.0000

Data Index: 1372310 (The Pile)

Max Activating Token Index: 931

Text #5

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0570. Min Act: -0.0000

Data Index: 1365417 (The Pile)

Max Activating Token Index: 825

Text #6

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0454. Min Act: -0.0000

Data Index: 782710 (The Pile)

Max Activating Token Index: 938

Text #7

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0450. Min Act: -0.0000

Data Index: 709764 (The Pile)

Max Activating Token Index: 687

Text #8

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0487. Min Act: -0.0000

Data Index: 1156557 (The Pile)

Max Activating Token Index: 896

Text #9

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0509. Min Act: -0.0000

Data Index: 869445 (The Pile)

Max Activating Token Index: 749

Text #10

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0437. Min Act: -0.0000

Data Index: 946913 (The Pile)

Max Activating Token Index: 729

Text #11

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0484. Min Act: -0.0000

Data Index: 734459 (The Pile)

Max Activating Token Index: 355

Text #12

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0510. Min Act: -0.0000

Data Index: 1630084 (The Pile)

Max Activating Token Index: 788

Text #13

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0495. Min Act: -0.0000

Data Index: 553784 (The Pile)

Max Activating Token Index: 452

Text #14

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0472. Min Act: -0.0000

Data Index: 1543930 (The Pile)

Max Activating Token Index: 891

Text #15

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0474. Min Act: -0.0000

Data Index: 1078680 (The Pile)

Max Activating Token Index: 72

Text #16

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0441. Min Act: -0.0000

Data Index: 180998 (The Pile)

Max Activating Token Index: 982

Text #17

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0450. Min Act: -0.0000

Data Index: 936068 (The Pile)

Max Activating Token Index: 918

Text #18

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0413. Min Act: -0.0000

Data Index: 1094231 (The Pile)

Max Activating Token Index: 824

Text #19

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0454. Min Act: -0.0000

Data Index: 473004 (The Pile)

Max Activating Token Index: 413