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

Dataset: The Pile

Neuron 4921 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: 3.1864. Min Range: -3.1864

Max Act: 3.1393. Min Act: -0.0000

Data Index: 1974843 (The Pile)

Max Activating Token Index: 772

Text #1

Max Range: 3.1864. Min Range: -3.1864

Max Act: 3.1024. Min Act: -0.0000

Data Index: 1693252 (The Pile)

Max Activating Token Index: 643

Text #2

Max Range: 3.1864. Min Range: -3.1864

Max Act: 3.0790. Min Act: 0.0000

Data Index: 1522405 (The Pile)

Max Activating Token Index: 656

Text #3

Max Range: 3.1864. Min Range: -3.1864

Max Act: 3.1864. Min Act: -0.0000

Data Index: 381543 (The Pile)

Max Activating Token Index: 614

Text #4

Max Range: 3.1864. Min Range: -3.1864

Max Act: 2.9904. Min Act: -0.0000

Data Index: 1777943 (The Pile)

Max Activating Token Index: 92

Text #5

Max Range: 3.1864. Min Range: -3.1864

Max Act: 2.8117. Min Act: -0.0000

Data Index: 1259259 (The Pile)

Max Activating Token Index: 733

Text #6

Max Range: 3.1864. Min Range: -3.1864

Max Act: 2.6196. Min Act: 0.0000

Data Index: 1925947 (The Pile)

Max Activating Token Index: 764

Text #7

Max Range: 3.1864. Min Range: -3.1864

Max Act: 2.4978. Min Act: 0.0000

Data Index: 1241713 (The Pile)

Max Activating Token Index: 987

Text #8

Max Range: 3.1864. Min Range: -3.1864

Max Act: 2.5049. Min Act: -0.0000

Data Index: 1988524 (The Pile)

Max Activating Token Index: 538

Text #9

Max Range: 3.1864. Min Range: -3.1864

Max Act: 2.3190. Min Act: -0.0000

Data Index: 108243 (The Pile)

Max Activating Token Index: 880

Text #10

Max Range: 3.1864. Min Range: -3.1864

Max Act: 2.2999. Min Act: -0.0000

Data Index: 995530 (The Pile)

Max Activating Token Index: 1004

Text #11

Max Range: 3.1864. Min Range: -3.1864

Max Act: 2.2402. Min Act: -0.0000

Data Index: 843860 (The Pile)

Max Activating Token Index: 451

Text #12

Max Range: 3.1864. Min Range: -3.1864

Max Act: 1.7743. Min Act: -0.0000

Data Index: 1800134 (The Pile)

Max Activating Token Index: 1013

Text #13

Max Range: 3.1864. Min Range: -3.1864

Max Act: 2.0058. Min Act: -0.0000

Data Index: 1879015 (The Pile)

Max Activating Token Index: 314

Text #14

Max Range: 3.1864. Min Range: -3.1864

Max Act: 1.9894. Min Act: -0.0000

Data Index: 1835277 (The Pile)

Max Activating Token Index: 597

Text #15

Max Range: 3.1864. Min Range: -3.1864

Max Act: 1.9846. Min Act: -0.0000

Data Index: 1046782 (The Pile)

Max Activating Token Index: 656

Text #16

Max Range: 3.1864. Min Range: -3.1864

Max Act: 1.9084. Min Act: -0.0000

Data Index: 1710902 (The Pile)

Max Activating Token Index: 962

Text #17

Max Range: 3.1864. Min Range: -3.1864

Max Act: 1.8570. Min Act: 0.0000

Data Index: 1658708 (The Pile)

Max Activating Token Index: 367

Text #18

Max Range: 3.1864. Min Range: -3.1864

Max Act: 1.9567. Min Act: -0.0000

Data Index: 1642103 (The Pile)

Max Activating Token Index: 38

Text #19

Max Range: 3.1864. Min Range: -3.1864

Max Act: 2.1910. Min Act: 0.0000

Data Index: 96412 (The Pile)

Max Activating Token Index: 933