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

Dataset: The Pile

Neuron 5 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.8769. Min Act: -0.0000

Data Index: 1058669 (The Pile)

Max Activating Token Index: 540

Text #1

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.6334. Min Act: -0.0000

Data Index: 234602 (The Pile)

Max Activating Token Index: 354

Text #2

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.5927. Min Act: -0.0000

Data Index: 271834 (The Pile)

Max Activating Token Index: 825

Text #3

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.6480. Min Act: -0.0000

Data Index: 1917034 (The Pile)

Max Activating Token Index: 197

Text #4

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.5530. Min Act: -0.0000

Data Index: 964302 (The Pile)

Max Activating Token Index: 747

Text #5

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.5723. Min Act: -0.0000

Data Index: 1448678 (The Pile)

Max Activating Token Index: 776

Text #6

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.5780. Min Act: -0.0000

Data Index: 799748 (The Pile)

Max Activating Token Index: 721

Text #7

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.5042. Min Act: -0.0000

Data Index: 617008 (The Pile)

Max Activating Token Index: 646

Text #8

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.5454. Min Act: -0.0000

Data Index: 1085466 (The Pile)

Max Activating Token Index: 746

Text #9

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.4940. Min Act: -0.0000

Data Index: 1712391 (The Pile)

Max Activating Token Index: 169

Text #10

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.4890. Min Act: -0.0000

Data Index: 1310951 (The Pile)

Max Activating Token Index: 803

Text #11

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.4671. Min Act: -0.0000

Data Index: 875305 (The Pile)

Max Activating Token Index: 336

Text #12

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.4815. Min Act: -0.0000

Data Index: 240166 (The Pile)

Max Activating Token Index: 469

Text #13

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.4515. Min Act: -0.0000

Data Index: 1369965 (The Pile)

Max Activating Token Index: 120

Text #14

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.4637. Min Act: -0.0000

Data Index: 446652 (The Pile)

Max Activating Token Index: 740

Text #15

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.5080. Min Act: -0.0000

Data Index: 240459 (The Pile)

Max Activating Token Index: 591

Text #16

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.4710. Min Act: -0.0000

Data Index: 182337 (The Pile)

Max Activating Token Index: 162

Text #17

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.4255. Min Act: -0.0000

Data Index: 720144 (The Pile)

Max Activating Token Index: 992

Text #18

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.4489. Min Act: -0.0000

Data Index: 428596 (The Pile)

Max Activating Token Index: 904

Text #19

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.4691. Min Act: -0.0000

Data Index: 1837964 (The Pile)

Max Activating Token Index: 1008