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

Dataset: The Pile

Neuron 3250 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: 0.3723. Min Range: -0.3723

Max Act: 0.3723. Min Act: -0.0000

Data Index: 525364 (The Pile)

Max Activating Token Index: 248

Text #1

Max Range: 0.3723. Min Range: -0.3723

Max Act: 0.3288. Min Act: -0.0000

Data Index: 1122794 (The Pile)

Max Activating Token Index: 1010

Text #2

Max Range: 0.3723. Min Range: -0.3723

Max Act: 0.3368. Min Act: -0.0000

Data Index: 658791 (The Pile)

Max Activating Token Index: 554

Text #3

Max Range: 0.3723. Min Range: -0.3723

Max Act: 0.3467. Min Act: -0.0000

Data Index: 527824 (The Pile)

Max Activating Token Index: 478

Text #4

Max Range: 0.3723. Min Range: -0.3723

Max Act: 0.3088. Min Act: -0.0000

Data Index: 1651386 (The Pile)

Max Activating Token Index: 327

Text #5

Max Range: 0.3723. Min Range: -0.3723

Max Act: 0.3083. Min Act: -0.0000

Data Index: 1017106 (The Pile)

Max Activating Token Index: 164

Text #6

Max Range: 0.3723. Min Range: -0.3723

Max Act: 0.3220. Min Act: -0.0000

Data Index: 1404537 (The Pile)

Max Activating Token Index: 235

Text #7

Max Range: 0.3723. Min Range: -0.3723

Max Act: 0.2948. Min Act: -0.0000

Data Index: 1501573 (The Pile)

Max Activating Token Index: 429

Text #8

Max Range: 0.3723. Min Range: -0.3723

Max Act: 0.3046. Min Act: -0.0000

Data Index: 1033323 (The Pile)

Max Activating Token Index: 989

Text #9

Max Range: 0.3723. Min Range: -0.3723

Max Act: 0.2976. Min Act: -0.0000

Data Index: 1932344 (The Pile)

Max Activating Token Index: 906

Text #10

Max Range: 0.3723. Min Range: -0.3723

Max Act: 0.2962. Min Act: -0.0000

Data Index: 334203 (The Pile)

Max Activating Token Index: 529

Text #11

Max Range: 0.3723. Min Range: -0.3723

Max Act: 0.3016. Min Act: -0.0000

Data Index: 437547 (The Pile)

Max Activating Token Index: 366

Text #12

Max Range: 0.3723. Min Range: -0.3723

Max Act: 0.2905. Min Act: -0.0000

Data Index: 1149021 (The Pile)

Max Activating Token Index: 255

Text #13

Max Range: 0.3723. Min Range: -0.3723

Max Act: 0.2865. Min Act: -0.0000

Data Index: 97478 (The Pile)

Max Activating Token Index: 231

Text #14

Max Range: 0.3723. Min Range: -0.3723

Max Act: 0.2859. Min Act: -0.0000

Data Index: 858531 (The Pile)

Max Activating Token Index: 472

Text #15

Max Range: 0.3723. Min Range: -0.3723

Max Act: 0.2850. Min Act: -0.0000

Data Index: 847697 (The Pile)

Max Activating Token Index: 883

Text #16

Max Range: 0.3723. Min Range: -0.3723

Max Act: 0.2855. Min Act: -0.0000

Data Index: 1168645 (The Pile)

Max Activating Token Index: 515

Text #17

Max Range: 0.3723. Min Range: -0.3723

Max Act: 0.2814. Min Act: -0.0000

Data Index: 177477 (The Pile)

Max Activating Token Index: 107

Text #18

Max Range: 0.3723. Min Range: -0.3723

Max Act: 0.2833. Min Act: -0.0000

Data Index: 1326867 (The Pile)

Max Activating Token Index: 336

Text #19

Max Range: 0.3723. Min Range: -0.3723

Max Act: 0.2729. Min Act: -0.0000

Data Index: 1437513 (The Pile)

Max Activating Token Index: 302