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

Dataset: The Pile

Neuron 4022 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.6567. Min Act: -0.0000

Data Index: 1413711 (The Pile)

Max Activating Token Index: 183

Text #1

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.5488. Min Act: -0.0000

Data Index: 788169 (The Pile)

Max Activating Token Index: 95

Text #2

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.5403. Min Act: -0.0000

Data Index: 694722 (The Pile)

Max Activating Token Index: 884

Text #3

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.5366. Min Act: -0.0000

Data Index: 1796048 (The Pile)

Max Activating Token Index: 436

Text #4

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.4929. Min Act: -0.0000

Data Index: 577907 (The Pile)

Max Activating Token Index: 423

Text #5

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.5447. Min Act: -0.0000

Data Index: 181276 (The Pile)

Max Activating Token Index: 238

Text #6

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.4994. Min Act: -0.0000

Data Index: 1474320 (The Pile)

Max Activating Token Index: 619

Text #7

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.4937. Min Act: -0.0000

Data Index: 711823 (The Pile)

Max Activating Token Index: 688

Text #8

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.4765. Min Act: -0.0000

Data Index: 1499782 (The Pile)

Max Activating Token Index: 524

Text #9

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.4532. Min Act: -0.0000

Data Index: 1802979 (The Pile)

Max Activating Token Index: 105

Text #10

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.4616. Min Act: -0.0000

Data Index: 654671 (The Pile)

Max Activating Token Index: 272

Text #11

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.4697. Min Act: -0.0000

Data Index: 755314 (The Pile)

Max Activating Token Index: 622

Text #12

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.4374. Min Act: -0.0000

Data Index: 1872909 (The Pile)

Max Activating Token Index: 515

Text #13

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.4415. Min Act: -0.0000

Data Index: 1610430 (The Pile)

Max Activating Token Index: 482

Text #14

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.4118. Min Act: -0.0000

Data Index: 5438 (The Pile)

Max Activating Token Index: 120

Text #15

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.4114. Min Act: -0.0000

Data Index: 1851120 (The Pile)

Max Activating Token Index: 280

Text #16

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.4220. Min Act: -0.0000

Data Index: 1862750 (The Pile)

Max Activating Token Index: 504

Text #17

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.3964. Min Act: -0.0000

Data Index: 1845329 (The Pile)

Max Activating Token Index: 281

Text #18

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.3781. Min Act: -0.0000

Data Index: 1488763 (The Pile)

Max Activating Token Index: 153

Text #19

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.3886. Min Act: -0.0000

Data Index: 928460 (The Pile)

Max Activating Token Index: 118