Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2912 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.8087. Min Act: -0.0000

Data Index: 10916 (The Pile)

Max Activating Token Index: 879

Text #1

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.7975. Min Act: -0.0000

Data Index: 1001483 (The Pile)

Max Activating Token Index: 276

Text #2

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.7578. Min Act: 0.0000

Data Index: 1458186 (The Pile)

Max Activating Token Index: 42

Text #3

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.7417. Min Act: -0.0000

Data Index: 1608416 (The Pile)

Max Activating Token Index: 331

Text #4

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.7973. Min Act: -0.0000

Data Index: 169407 (The Pile)

Max Activating Token Index: 622

Text #5

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.7079. Min Act: -0.0000

Data Index: 1965079 (The Pile)

Max Activating Token Index: 111

Text #6

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.7458. Min Act: -0.0000

Data Index: 1777911 (The Pile)

Max Activating Token Index: 582

Text #7

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.7123. Min Act: -0.0000

Data Index: 35612 (The Pile)

Max Activating Token Index: 81

Text #8

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.7112. Min Act: -0.0000

Data Index: 1303758 (The Pile)

Max Activating Token Index: 989

Text #9

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.7251. Min Act: -0.0000

Data Index: 1394010 (The Pile)

Max Activating Token Index: 48

Text #10

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.6690. Min Act: -0.0000

Data Index: 18569 (The Pile)

Max Activating Token Index: 424

Text #11

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.6862. Min Act: -0.0000

Data Index: 1092746 (The Pile)

Max Activating Token Index: 303

Text #12

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.7199. Min Act: -0.0000

Data Index: 746956 (The Pile)

Max Activating Token Index: 460

Text #13

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.6944. Min Act: -0.0000

Data Index: 964764 (The Pile)

Max Activating Token Index: 610

Text #14

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.6602. Min Act: -0.0000

Data Index: 1919668 (The Pile)

Max Activating Token Index: 750

Text #15

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.6411. Min Act: -0.0000

Data Index: 932210 (The Pile)

Max Activating Token Index: 544

Text #16

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.6358. Min Act: -0.0000

Data Index: 686550 (The Pile)

Max Activating Token Index: 530

Text #17

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.6701. Min Act: 0.0000

Data Index: 417880 (The Pile)

Max Activating Token Index: 330

Text #18

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.6626. Min Act: -0.0000

Data Index: 629043 (The Pile)

Max Activating Token Index: 363

Text #19

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.5896. Min Act: -0.0000

Data Index: 454360 (The Pile)

Max Activating Token Index: 579