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

Dataset: The Pile

Neuron 1256 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.5867. Min Act: -0.0000

Data Index: 1897569 (The Pile)

Max Activating Token Index: 774

Text #1

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.5482. Min Act: -0.0000

Data Index: 619096 (The Pile)

Max Activating Token Index: 950

Text #2

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4573. Min Act: 0.0000

Data Index: 1498741 (The Pile)

Max Activating Token Index: 109

Text #3

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4755. Min Act: -0.0000

Data Index: 1860744 (The Pile)

Max Activating Token Index: 368

Text #4

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4645. Min Act: -0.0000

Data Index: 671296 (The Pile)

Max Activating Token Index: 224

Text #5

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4384. Min Act: -0.0000

Data Index: 547967 (The Pile)

Max Activating Token Index: 510

Text #6

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4487. Min Act: 0.0000

Data Index: 1816931 (The Pile)

Max Activating Token Index: 327

Text #7

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4322. Min Act: -0.0000

Data Index: 22604 (The Pile)

Max Activating Token Index: 255

Text #8

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4357. Min Act: 0.0000

Data Index: 686520 (The Pile)

Max Activating Token Index: 696

Text #9

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4094. Min Act: 0.0003

Data Index: 1233534 (The Pile)

Max Activating Token Index: 569

Text #10

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4125. Min Act: -0.0000

Data Index: 1124385 (The Pile)

Max Activating Token Index: 123

Text #11

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.3839. Min Act: -0.0000

Data Index: 1923828 (The Pile)

Max Activating Token Index: 530

Text #12

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.3567. Min Act: -0.0000

Data Index: 32067 (The Pile)

Max Activating Token Index: 705

Text #13

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.3383. Min Act: -0.0000

Data Index: 1475954 (The Pile)

Max Activating Token Index: 569

Text #14

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.3290. Min Act: -0.0000

Data Index: 152472 (The Pile)

Max Activating Token Index: 403

Text #15

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.3236. Min Act: -0.0000

Data Index: 719821 (The Pile)

Max Activating Token Index: 515

Text #16

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.3069. Min Act: -0.0000

Data Index: 183789 (The Pile)

Max Activating Token Index: 698

Text #17

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.3131. Min Act: -0.0000

Data Index: 1065702 (The Pile)

Max Activating Token Index: 868

Text #18

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.2976. Min Act: -0.0000

Data Index: 1396085 (The Pile)

Max Activating Token Index: 213

Text #19

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.3065. Min Act: 0.0000

Data Index: 655014 (The Pile)

Max Activating Token Index: 147