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

Dataset: The Pile

Neuron 449 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: 1.0839. Min Range: -1.0839

Max Act: 1.0422. Min Act: -0.0000

Data Index: 1099578 (The Pile)

Max Activating Token Index: 1008

Text #1

Max Range: 1.0839. Min Range: -1.0839

Max Act: 1.0839. Min Act: -0.0000

Data Index: 454397 (The Pile)

Max Activating Token Index: 583

Text #2

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.8902. Min Act: -0.0000

Data Index: 388701 (The Pile)

Max Activating Token Index: 891

Text #3

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.8753. Min Act: -0.0000

Data Index: 1506323 (The Pile)

Max Activating Token Index: 966

Text #4

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.9400. Min Act: -0.0000

Data Index: 831934 (The Pile)

Max Activating Token Index: 809

Text #5

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.9721. Min Act: -0.0000

Data Index: 1470002 (The Pile)

Max Activating Token Index: 919

Text #6

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.7936. Min Act: -0.0000

Data Index: 190607 (The Pile)

Max Activating Token Index: 603

Text #7

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.7997. Min Act: -0.0000

Data Index: 1177472 (The Pile)

Max Activating Token Index: 901

Text #8

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.7941. Min Act: -0.0000

Data Index: 1330028 (The Pile)

Max Activating Token Index: 690

Text #9

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.5961. Min Act: -0.0000

Data Index: 884232 (The Pile)

Max Activating Token Index: 957

Text #10

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.6072. Min Act: -0.0000

Data Index: 464719 (The Pile)

Max Activating Token Index: 808

Text #11

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.7456. Min Act: -0.0000

Data Index: 327462 (The Pile)

Max Activating Token Index: 679

Text #12

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.6758. Min Act: -0.0000

Data Index: 1858199 (The Pile)

Max Activating Token Index: 344

Text #13

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.7044. Min Act: -0.0000

Data Index: 1422576 (The Pile)

Max Activating Token Index: 371

Text #14

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.7293. Min Act: -0.0000

Data Index: 487869 (The Pile)

Max Activating Token Index: 415

Text #15

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.6107. Min Act: -0.0000

Data Index: 1265945 (The Pile)

Max Activating Token Index: 817

Text #16

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.5080. Min Act: -0.0000

Data Index: 128620 (The Pile)

Max Activating Token Index: 949

Text #17

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.5200. Min Act: -0.0000

Data Index: 784255 (The Pile)

Max Activating Token Index: 396

Text #18

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.4992. Min Act: -0.0000

Data Index: 1052419 (The Pile)

Max Activating Token Index: 732

Text #19

Max Range: 1.0839. Min Range: -1.0839

Max Act: 0.5035. Min Act: -0.0000

Data Index: 1042204 (The Pile)

Max Activating Token Index: 878