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

Dataset: The Pile

Neuron 1583 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: 0.6656. Min Range: -0.6656

Max Act: 0.6656. Min Act: -0.0000

Data Index: 849744 (The Pile)

Max Activating Token Index: 270

Text #1

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.5964. Min Act: -0.0000

Data Index: 1475439 (The Pile)

Max Activating Token Index: 624

Text #2

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.5741. Min Act: -0.0000

Data Index: 1674347 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.6443. Min Act: -0.0000

Data Index: 1693604 (The Pile)

Max Activating Token Index: 429

Text #4

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4891. Min Act: -0.0000

Data Index: 1898722 (The Pile)

Max Activating Token Index: 118

Text #5

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.5523. Min Act: -0.0000

Data Index: 159812 (The Pile)

Max Activating Token Index: 37

Text #6

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.5243. Min Act: -0.0000

Data Index: 971769 (The Pile)

Max Activating Token Index: 378

Text #7

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.5248. Min Act: -0.0000

Data Index: 108114 (The Pile)

Max Activating Token Index: 312

Text #8

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.5167. Min Act: -0.0000

Data Index: 1725809 (The Pile)

Max Activating Token Index: 997

Text #9

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.5219. Min Act: -0.0000

Data Index: 992491 (The Pile)

Max Activating Token Index: 687

Text #10

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.5497. Min Act: -0.0000

Data Index: 1077844 (The Pile)

Max Activating Token Index: 79

Text #11

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4579. Min Act: -0.0000

Data Index: 236762 (The Pile)

Max Activating Token Index: 183

Text #12

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4862. Min Act: -0.0000

Data Index: 426286 (The Pile)

Max Activating Token Index: 427

Text #13

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4816. Min Act: -0.0000

Data Index: 1844096 (The Pile)

Max Activating Token Index: 352

Text #14

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4756. Min Act: -0.0000

Data Index: 143183 (The Pile)

Max Activating Token Index: 348

Text #15

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.5219. Min Act: -0.0000

Data Index: 1017447 (The Pile)

Max Activating Token Index: 607

Text #16

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4622. Min Act: -0.0000

Data Index: 687361 (The Pile)

Max Activating Token Index: 364

Text #17

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4734. Min Act: -0.0000

Data Index: 1657389 (The Pile)

Max Activating Token Index: 195

Text #18

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4688. Min Act: -0.0000

Data Index: 1544582 (The Pile)

Max Activating Token Index: 189

Text #19

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4437. Min Act: -0.0000

Data Index: 396239 (The Pile)

Max Activating Token Index: 154