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

Dataset: The Pile

Neuron 1094 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: 1.8958. Min Range: -1.8958

Max Act: 1.8958. Min Act: -0.0000

Data Index: 1474482 (The Pile)

Max Activating Token Index: 398

Text #1

Max Range: 1.8958. Min Range: -1.8958

Max Act: 1.7347. Min Act: -0.0000

Data Index: 271766 (The Pile)

Max Activating Token Index: 165

Text #2

Max Range: 1.8958. Min Range: -1.8958

Max Act: 1.4619. Min Act: -0.0000

Data Index: 1491215 (The Pile)

Max Activating Token Index: 534

Text #3

Max Range: 1.8958. Min Range: -1.8958

Max Act: 1.4909. Min Act: -0.0000

Data Index: 329420 (The Pile)

Max Activating Token Index: 169

Text #4

Max Range: 1.8958. Min Range: -1.8958

Max Act: 1.3451. Min Act: -0.0000

Data Index: 1085544 (The Pile)

Max Activating Token Index: 377

Text #5

Max Range: 1.8958. Min Range: -1.8958

Max Act: 1.2543. Min Act: -0.0000

Data Index: 1404830 (The Pile)

Max Activating Token Index: 1014

Text #6

Max Range: 1.8958. Min Range: -1.8958

Max Act: 1.2885. Min Act: -0.0000

Data Index: 593024 (The Pile)

Max Activating Token Index: 748

Text #7

Max Range: 1.8958. Min Range: -1.8958

Max Act: 1.4149. Min Act: -0.0000

Data Index: 1859100 (The Pile)

Max Activating Token Index: 311

Text #8

Max Range: 1.8958. Min Range: -1.8958

Max Act: 1.2574. Min Act: -0.0000

Data Index: 115429 (The Pile)

Max Activating Token Index: 406

Text #9

Max Range: 1.8958. Min Range: -1.8958

Max Act: 1.2904. Min Act: -0.0000

Data Index: 279803 (The Pile)

Max Activating Token Index: 365

Text #10

Max Range: 1.8958. Min Range: -1.8958

Max Act: 1.0129. Min Act: -0.0000

Data Index: 264322 (The Pile)

Max Activating Token Index: 42

Text #11

Max Range: 1.8958. Min Range: -1.8958

Max Act: 1.2423. Min Act: -0.0000

Data Index: 291408 (The Pile)

Max Activating Token Index: 37

Text #12

Max Range: 1.8958. Min Range: -1.8958

Max Act: 1.1921. Min Act: -0.0000

Data Index: 412899 (The Pile)

Max Activating Token Index: 944

Text #13

Max Range: 1.8958. Min Range: -1.8958

Max Act: 1.2303. Min Act: -0.0000

Data Index: 1352850 (The Pile)

Max Activating Token Index: 846

Text #14

Max Range: 1.8958. Min Range: -1.8958

Max Act: 1.2153. Min Act: -0.0000

Data Index: 1709370 (The Pile)

Max Activating Token Index: 786

Text #15

Max Range: 1.8958. Min Range: -1.8958

Max Act: 1.2767. Min Act: -0.0000

Data Index: 1092608 (The Pile)

Max Activating Token Index: 367

Text #16

Max Range: 1.8958. Min Range: -1.8958

Max Act: 1.2402. Min Act: -0.0000

Data Index: 1592126 (The Pile)

Max Activating Token Index: 82

Text #17

Max Range: 1.8958. Min Range: -1.8958

Max Act: 1.1836. Min Act: -0.0000

Data Index: 1464645 (The Pile)

Max Activating Token Index: 449

Text #18

Max Range: 1.8958. Min Range: -1.8958

Max Act: 1.2128. Min Act: -0.0000

Data Index: 1036118 (The Pile)

Max Activating Token Index: 557

Text #19

Max Range: 1.8958. Min Range: -1.8958

Max Act: 1.2051. Min Act: -0.0000

Data Index: 188785 (The Pile)

Max Activating Token Index: 35