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

Dataset: The Pile

Neuron 482 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: 1.8626. Min Range: -1.8626

Max Act: 1.8626. Min Act: -0.0000

Data Index: 1910323 (The Pile)

Max Activating Token Index: 272

Text #1

Max Range: 1.8626. Min Range: -1.8626

Max Act: 1.6904. Min Act: -0.0000

Data Index: 1909871 (The Pile)

Max Activating Token Index: 742

Text #2

Max Range: 1.8626. Min Range: -1.8626

Max Act: 1.6612. Min Act: -0.0000

Data Index: 1938451 (The Pile)

Max Activating Token Index: 550

Text #3

Max Range: 1.8626. Min Range: -1.8626

Max Act: 1.4299. Min Act: -0.0000

Data Index: 765135 (The Pile)

Max Activating Token Index: 751

Text #4

Max Range: 1.8626. Min Range: -1.8626

Max Act: 1.6135. Min Act: -0.0000

Data Index: 1505215 (The Pile)

Max Activating Token Index: 1019

Text #5

Max Range: 1.8626. Min Range: -1.8626

Max Act: 1.6155. Min Act: -0.0000

Data Index: 231761 (The Pile)

Max Activating Token Index: 418

Text #6

Max Range: 1.8626. Min Range: -1.8626

Max Act: 1.6524. Min Act: -0.0000

Data Index: 247289 (The Pile)

Max Activating Token Index: 875

Text #7

Max Range: 1.8626. Min Range: -1.8626

Max Act: 1.4988. Min Act: -0.0000

Data Index: 1177538 (The Pile)

Max Activating Token Index: 823

Text #8

Max Range: 1.8626. Min Range: -1.8626

Max Act: 1.5404. Min Act: -0.0000

Data Index: 1645067 (The Pile)

Max Activating Token Index: 141

Text #9

Max Range: 1.8626. Min Range: -1.8626

Max Act: 1.4784. Min Act: -0.0000

Data Index: 1413810 (The Pile)

Max Activating Token Index: 883

Text #10

Max Range: 1.8626. Min Range: -1.8626

Max Act: 1.4878. Min Act: -0.0000

Data Index: 322143 (The Pile)

Max Activating Token Index: 509

Text #11

Max Range: 1.8626. Min Range: -1.8626

Max Act: 1.4637. Min Act: -0.0000

Data Index: 1821851 (The Pile)

Max Activating Token Index: 726

Text #12

Max Range: 1.8626. Min Range: -1.8626

Max Act: 1.3744. Min Act: -0.0000

Data Index: 1605262 (The Pile)

Max Activating Token Index: 806

Text #13

Max Range: 1.8626. Min Range: -1.8626

Max Act: 1.3681. Min Act: -0.0000

Data Index: 316339 (The Pile)

Max Activating Token Index: 406

Text #14

Max Range: 1.8626. Min Range: -1.8626

Max Act: 1.5371. Min Act: -0.0000

Data Index: 1143494 (The Pile)

Max Activating Token Index: 470

Text #15

Max Range: 1.8626. Min Range: -1.8626

Max Act: 1.5349. Min Act: -0.0000

Data Index: 1513938 (The Pile)

Max Activating Token Index: 224

Text #16

Max Range: 1.8626. Min Range: -1.8626

Max Act: 1.4409. Min Act: -0.0000

Data Index: 1677970 (The Pile)

Max Activating Token Index: 674

Text #17

Max Range: 1.8626. Min Range: -1.8626

Max Act: 1.4300. Min Act: -0.0000

Data Index: 1779774 (The Pile)

Max Activating Token Index: 618

Text #18

Max Range: 1.8626. Min Range: -1.8626

Max Act: 1.4108. Min Act: -0.0000

Data Index: 174193 (The Pile)

Max Activating Token Index: 568

Text #19

Max Range: 1.8626. Min Range: -1.8626

Max Act: 1.3980. Min Act: -0.0000

Data Index: 1606653 (The Pile)

Max Activating Token Index: 850