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

Dataset: The Pile

Neuron 94 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2719. Min Act: -0.0000

Data Index: 492103 (The Pile)

Max Activating Token Index: 46

Text #1

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2627. Min Act: -0.0000

Data Index: 1447827 (The Pile)

Max Activating Token Index: 685

Text #2

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2438. Min Act: -0.0000

Data Index: 1954823 (The Pile)

Max Activating Token Index: 101

Text #3

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2575. Min Act: -0.0000

Data Index: 1452960 (The Pile)

Max Activating Token Index: 116

Text #4

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2316. Min Act: -0.0000

Data Index: 992154 (The Pile)

Max Activating Token Index: 319

Text #5

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2092. Min Act: -0.0000

Data Index: 1039774 (The Pile)

Max Activating Token Index: 398

Text #6

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2266. Min Act: -0.0000

Data Index: 534042 (The Pile)

Max Activating Token Index: 89

Text #7

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.1927. Min Act: -0.0000

Data Index: 443361 (The Pile)

Max Activating Token Index: 664

Text #8

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2047. Min Act: -0.0000

Data Index: 654586 (The Pile)

Max Activating Token Index: 223

Text #9

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.1838. Min Act: -0.0000

Data Index: 737916 (The Pile)

Max Activating Token Index: 821

Text #10

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.1907. Min Act: -0.0000

Data Index: 697789 (The Pile)

Max Activating Token Index: 801

Text #11

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.1902. Min Act: -0.0000

Data Index: 1789140 (The Pile)

Max Activating Token Index: 104

Text #12

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.1930. Min Act: -0.0000

Data Index: 964774 (The Pile)

Max Activating Token Index: 184

Text #13

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.1933. Min Act: -0.0000

Data Index: 1489836 (The Pile)

Max Activating Token Index: 37

Text #14

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.1615. Min Act: -0.0000

Data Index: 650901 (The Pile)

Max Activating Token Index: 407

Text #15

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.1848. Min Act: -0.0000

Data Index: 915862 (The Pile)

Max Activating Token Index: 900

Text #16

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.1817. Min Act: -0.0000

Data Index: 104331 (The Pile)

Max Activating Token Index: 523

Text #17

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.1914. Min Act: -0.0000

Data Index: 1094228 (The Pile)

Max Activating Token Index: 919

Text #18

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.1723. Min Act: -0.0000

Data Index: 485824 (The Pile)

Max Activating Token Index: 305

Text #19

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.1747. Min Act: -0.0000

Data Index: 1741639 (The Pile)

Max Activating Token Index: 629