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

Dataset: The Pile

Neuron 3840 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1909. Min Range: -3.1909

Max Act: 3.0997. Min Act: -0.0000

Data Index: 1897825 (The Pile)

Max Activating Token Index: 931

Text #1

Max Range: 3.1909. Min Range: -3.1909

Max Act: 3.1909. Min Act: -0.0000

Data Index: 1220985 (The Pile)

Max Activating Token Index: 447

Text #2

Max Range: 3.1909. Min Range: -3.1909

Max Act: 2.9706. Min Act: -0.0000

Data Index: 754637 (The Pile)

Max Activating Token Index: 149

Text #3

Max Range: 3.1909. Min Range: -3.1909

Max Act: 3.0734. Min Act: -0.0000

Data Index: 376215 (The Pile)

Max Activating Token Index: 325

Text #4

Max Range: 3.1909. Min Range: -3.1909

Max Act: 3.1903. Min Act: -0.0000

Data Index: 380760 (The Pile)

Max Activating Token Index: 833

Text #5

Max Range: 3.1909. Min Range: -3.1909

Max Act: 2.6310. Min Act: -0.0000

Data Index: 1138423 (The Pile)

Max Activating Token Index: 890

Text #6

Max Range: 3.1909. Min Range: -3.1909

Max Act: 2.8900. Min Act: -0.0000

Data Index: 1390760 (The Pile)

Max Activating Token Index: 46

Text #7

Max Range: 3.1909. Min Range: -3.1909

Max Act: 2.9242. Min Act: -0.0000

Data Index: 886235 (The Pile)

Max Activating Token Index: 564

Text #8

Max Range: 3.1909. Min Range: -3.1909

Max Act: 3.0049. Min Act: -0.0000

Data Index: 1572836 (The Pile)

Max Activating Token Index: 255

Text #9

Max Range: 3.1909. Min Range: -3.1909

Max Act: 2.8001. Min Act: -0.0000

Data Index: 1508303 (The Pile)

Max Activating Token Index: 261

Text #10

Max Range: 3.1909. Min Range: -3.1909

Max Act: 2.7882. Min Act: -0.0000

Data Index: 477179 (The Pile)

Max Activating Token Index: 644

Text #11

Max Range: 3.1909. Min Range: -3.1909

Max Act: 2.6708. Min Act: -0.0000

Data Index: 1310799 (The Pile)

Max Activating Token Index: 935

Text #12

Max Range: 3.1909. Min Range: -3.1909

Max Act: 2.6445. Min Act: -0.0000

Data Index: 1379308 (The Pile)

Max Activating Token Index: 77

Text #13

Max Range: 3.1909. Min Range: -3.1909

Max Act: 2.6445. Min Act: -0.0000

Data Index: 797245 (The Pile)

Max Activating Token Index: 424

Text #14

Max Range: 3.1909. Min Range: -3.1909

Max Act: 2.6401. Min Act: -0.0000

Data Index: 312825 (The Pile)

Max Activating Token Index: 132

Text #15

Max Range: 3.1909. Min Range: -3.1909

Max Act: 2.6086. Min Act: -0.0000

Data Index: 462958 (The Pile)

Max Activating Token Index: 72

Text #16

Max Range: 3.1909. Min Range: -3.1909

Max Act: 2.8778. Min Act: -0.0000

Data Index: 1293283 (The Pile)

Max Activating Token Index: 464

Text #17

Max Range: 3.1909. Min Range: -3.1909

Max Act: 2.5873. Min Act: -0.0000

Data Index: 933920 (The Pile)

Max Activating Token Index: 14

Text #18

Max Range: 3.1909. Min Range: -3.1909

Max Act: 2.8233. Min Act: -0.0000

Data Index: 980848 (The Pile)

Max Activating Token Index: 427

Text #19

Max Range: 3.1909. Min Range: -3.1909

Max Act: 2.3680. Min Act: -0.0000

Data Index: 1813155 (The Pile)

Max Activating Token Index: 685