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

Dataset: The Pile

Neuron 3156 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.6868. Min Act: -0.0000

Data Index: 1229448 (The Pile)

Max Activating Token Index: 855

Text #1

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.4849. Min Act: -0.0000

Data Index: 448810 (The Pile)

Max Activating Token Index: 81

Text #2

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.3818. Min Act: -0.0000

Data Index: 1238648 (The Pile)

Max Activating Token Index: 159

Text #3

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.3280. Min Act: -0.0000

Data Index: 1107210 (The Pile)

Max Activating Token Index: 220

Text #4

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.3253. Min Act: -0.0000

Data Index: 379025 (The Pile)

Max Activating Token Index: 50

Text #5

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.3287. Min Act: -0.0000

Data Index: 1702772 (The Pile)

Max Activating Token Index: 499

Text #6

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.3160. Min Act: -0.0000

Data Index: 741888 (The Pile)

Max Activating Token Index: 375

Text #7

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.3768. Min Act: -0.0000

Data Index: 1502888 (The Pile)

Max Activating Token Index: 697

Text #8

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.2975. Min Act: -0.0000

Data Index: 1980677 (The Pile)

Max Activating Token Index: 37

Text #9

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.3065. Min Act: -0.0000

Data Index: 1868270 (The Pile)

Max Activating Token Index: 327

Text #10

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.2827. Min Act: -0.0000

Data Index: 979465 (The Pile)

Max Activating Token Index: 145

Text #11

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.3000. Min Act: -0.0000

Data Index: 756215 (The Pile)

Max Activating Token Index: 493

Text #12

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.2973. Min Act: -0.0000

Data Index: 233853 (The Pile)

Max Activating Token Index: 179

Text #13

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.2871. Min Act: -0.0000

Data Index: 1671879 (The Pile)

Max Activating Token Index: 299

Text #14

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.2690. Min Act: -0.0000

Data Index: 603834 (The Pile)

Max Activating Token Index: 189

Text #15

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.2633. Min Act: -0.0000

Data Index: 987292 (The Pile)

Max Activating Token Index: 294

Text #16

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.3001. Min Act: -0.0000

Data Index: 1165556 (The Pile)

Max Activating Token Index: 519

Text #17

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.2805. Min Act: -0.0000

Data Index: 1098910 (The Pile)

Max Activating Token Index: 55

Text #18

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.2549. Min Act: -0.0000

Data Index: 956936 (The Pile)

Max Activating Token Index: 877

Text #19

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.2791. Min Act: -0.0000

Data Index: 521091 (The Pile)

Max Activating Token Index: 441