Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2822 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3831. Min Range: -1.3831

Max Act: 1.3831. Min Act: -0.0000

Data Index: 536583 (The Pile)

Max Activating Token Index: 449

Text #1

Max Range: 1.3831. Min Range: -1.3831

Max Act: 1.1330. Min Act: -0.0000

Data Index: 690287 (The Pile)

Max Activating Token Index: 894

Text #2

Max Range: 1.3831. Min Range: -1.3831

Max Act: 1.0693. Min Act: -0.0000

Data Index: 961620 (The Pile)

Max Activating Token Index: 649

Text #3

Max Range: 1.3831. Min Range: -1.3831

Max Act: 1.0640. Min Act: -0.0000

Data Index: 405723 (The Pile)

Max Activating Token Index: 329

Text #4

Max Range: 1.3831. Min Range: -1.3831

Max Act: 1.0887. Min Act: -0.0000

Data Index: 718721 (The Pile)

Max Activating Token Index: 105

Text #5

Max Range: 1.3831. Min Range: -1.3831

Max Act: 0.9778. Min Act: -0.0000

Data Index: 1138137 (The Pile)

Max Activating Token Index: 803

Text #6

Max Range: 1.3831. Min Range: -1.3831

Max Act: 1.0009. Min Act: -0.0000

Data Index: 1304855 (The Pile)

Max Activating Token Index: 456

Text #7

Max Range: 1.3831. Min Range: -1.3831

Max Act: 0.9665. Min Act: -0.0000

Data Index: 237138 (The Pile)

Max Activating Token Index: 532

Text #8

Max Range: 1.3831. Min Range: -1.3831

Max Act: 0.9346. Min Act: -0.0000

Data Index: 1929346 (The Pile)

Max Activating Token Index: 289

Text #9

Max Range: 1.3831. Min Range: -1.3831

Max Act: 0.9697. Min Act: -0.0000

Data Index: 1192445 (The Pile)

Max Activating Token Index: 543

Text #10

Max Range: 1.3831. Min Range: -1.3831

Max Act: 0.9897. Min Act: -0.0000

Data Index: 634484 (The Pile)

Max Activating Token Index: 862

Text #11

Max Range: 1.3831. Min Range: -1.3831

Max Act: 0.8896. Min Act: -0.0000

Data Index: 1688499 (The Pile)

Max Activating Token Index: 121

Text #12

Max Range: 1.3831. Min Range: -1.3831

Max Act: 0.9449. Min Act: -0.0000

Data Index: 1393285 (The Pile)

Max Activating Token Index: 685

Text #13

Max Range: 1.3831. Min Range: -1.3831

Max Act: 0.9489. Min Act: -0.0000

Data Index: 295513 (The Pile)

Max Activating Token Index: 730

Text #14

Max Range: 1.3831. Min Range: -1.3831

Max Act: 0.9338. Min Act: -0.0000

Data Index: 965400 (The Pile)

Max Activating Token Index: 516

Text #15

Max Range: 1.3831. Min Range: -1.3831

Max Act: 0.7715. Min Act: -0.0000

Data Index: 1581618 (The Pile)

Max Activating Token Index: 116

Text #16

Max Range: 1.3831. Min Range: -1.3831

Max Act: 0.9337. Min Act: -0.0000

Data Index: 1657632 (The Pile)

Max Activating Token Index: 465

Text #17

Max Range: 1.3831. Min Range: -1.3831

Max Act: 0.8770. Min Act: -0.0000

Data Index: 1035238 (The Pile)

Max Activating Token Index: 331

Text #18

Max Range: 1.3831. Min Range: -1.3831

Max Act: 0.8478. Min Act: -0.0000

Data Index: 529644 (The Pile)

Max Activating Token Index: 220

Text #19

Max Range: 1.3831. Min Range: -1.3831

Max Act: 0.7113. Min Act: -0.0000

Data Index: 1476053 (The Pile)

Max Activating Token Index: 616