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

Dataset: The Pile

Neuron 3675 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.3650. Min Act: -0.0000

Data Index: 1185317 (The Pile)

Max Activating Token Index: 414

Text #1

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.3606. Min Act: -0.0000

Data Index: 1645208 (The Pile)

Max Activating Token Index: 871

Text #2

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.3680. Min Act: -0.0000

Data Index: 1098648 (The Pile)

Max Activating Token Index: 498

Text #3

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.3490. Min Act: -0.0000

Data Index: 1473489 (The Pile)

Max Activating Token Index: 447

Text #4

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.3651. Min Act: -0.0000

Data Index: 1198196 (The Pile)

Max Activating Token Index: 647

Text #5

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.3474. Min Act: -0.0000

Data Index: 736686 (The Pile)

Max Activating Token Index: 488

Text #6

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.3540. Min Act: -0.0000

Data Index: 1648493 (The Pile)

Max Activating Token Index: 511

Text #7

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.3421. Min Act: -0.0000

Data Index: 1818359 (The Pile)

Max Activating Token Index: 145

Text #8

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.3142. Min Act: -0.0000

Data Index: 1668595 (The Pile)

Max Activating Token Index: 817

Text #9

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.3198. Min Act: -0.0000

Data Index: 1821527 (The Pile)

Max Activating Token Index: 801

Text #10

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.3341. Min Act: -0.0000

Data Index: 870517 (The Pile)

Max Activating Token Index: 585

Text #11

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.3477. Min Act: 0.0000

Data Index: 1123094 (The Pile)

Max Activating Token Index: 159

Text #12

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.3552. Min Act: -0.0000

Data Index: 296356 (The Pile)

Max Activating Token Index: 1022

Text #13

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.3411. Min Act: -0.0000

Data Index: 1082225 (The Pile)

Max Activating Token Index: 603

Text #14

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.3101. Min Act: -0.0000

Data Index: 1207408 (The Pile)

Max Activating Token Index: 918

Text #15

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.3516. Min Act: -0.0000

Data Index: 1147746 (The Pile)

Max Activating Token Index: 213

Text #16

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.3167. Min Act: -0.0000

Data Index: 171388 (The Pile)

Max Activating Token Index: 522

Text #17

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.3174. Min Act: -0.0000

Data Index: 1097507 (The Pile)

Max Activating Token Index: 202

Text #18

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.2987. Min Act: -0.0000

Data Index: 699848 (The Pile)

Max Activating Token Index: 855

Text #19

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.3145. Min Act: 0.0000

Data Index: 820706 (The Pile)

Max Activating Token Index: 502