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

Dataset: The Pile

Neuron 2641 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.9112. Min Act: -0.0000

Data Index: 337525 (The Pile)

Max Activating Token Index: 897

Text #1

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.9600. Min Act: -0.0000

Data Index: 457104 (The Pile)

Max Activating Token Index: 206

Text #2

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.8753. Min Act: -0.0000

Data Index: 872825 (The Pile)

Max Activating Token Index: 654

Text #3

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.8520. Min Act: 0.0000

Data Index: 493516 (The Pile)

Max Activating Token Index: 908

Text #4

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7402. Min Act: 0.0000

Data Index: 1063037 (The Pile)

Max Activating Token Index: 474

Text #5

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7224. Min Act: -0.0000

Data Index: 676190 (The Pile)

Max Activating Token Index: 638

Text #6

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7484. Min Act: -0.0000

Data Index: 1496594 (The Pile)

Max Activating Token Index: 39

Text #7

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7102. Min Act: -0.0000

Data Index: 538319 (The Pile)

Max Activating Token Index: 715

Text #8

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7552. Min Act: -0.0000

Data Index: 1809082 (The Pile)

Max Activating Token Index: 75

Text #9

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7297. Min Act: -0.0000

Data Index: 666806 (The Pile)

Max Activating Token Index: 979

Text #10

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7087. Min Act: -0.0000

Data Index: 212980 (The Pile)

Max Activating Token Index: 654

Text #11

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.6793. Min Act: -0.0000

Data Index: 1251114 (The Pile)

Max Activating Token Index: 76

Text #12

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7135. Min Act: -0.0000

Data Index: 281823 (The Pile)

Max Activating Token Index: 77

Text #13

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7159. Min Act: -0.0000

Data Index: 1342656 (The Pile)

Max Activating Token Index: 72

Text #14

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7033. Min Act: -0.0000

Data Index: 609672 (The Pile)

Max Activating Token Index: 738

Text #15

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.6530. Min Act: -0.0000

Data Index: 1695229 (The Pile)

Max Activating Token Index: 774

Text #16

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.6921. Min Act: -0.0000

Data Index: 818266 (The Pile)

Max Activating Token Index: 529

Text #17

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7007. Min Act: -0.0001

Data Index: 200257 (The Pile)

Max Activating Token Index: 929

Text #18

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.6812. Min Act: -0.0000

Data Index: 1206132 (The Pile)

Max Activating Token Index: 984

Text #19

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7160. Min Act: -0.0000

Data Index: 104087 (The Pile)

Max Activating Token Index: 632