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

Dataset: The Pile

Neuron 4489 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: 0.3647. Min Range: -0.3647

Max Act: 0.3647. Min Act: -0.0000

Data Index: 1152558 (The Pile)

Max Activating Token Index: 136

Text #1

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2730. Min Act: -0.0000

Data Index: 903914 (The Pile)

Max Activating Token Index: 187

Text #2

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2700. Min Act: -0.0000

Data Index: 1788327 (The Pile)

Max Activating Token Index: 136

Text #3

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.3127. Min Act: -0.0000

Data Index: 547325 (The Pile)

Max Activating Token Index: 780

Text #4

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2820. Min Act: -0.0000

Data Index: 129043 (The Pile)

Max Activating Token Index: 378

Text #5

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2941. Min Act: -0.0000

Data Index: 1884847 (The Pile)

Max Activating Token Index: 369

Text #6

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2750. Min Act: -0.0000

Data Index: 1397699 (The Pile)

Max Activating Token Index: 969

Text #7

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2733. Min Act: -0.0000

Data Index: 989622 (The Pile)

Max Activating Token Index: 582

Text #8

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2722. Min Act: -0.0000

Data Index: 246437 (The Pile)

Max Activating Token Index: 564

Text #9

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2532. Min Act: -0.0000

Data Index: 1240341 (The Pile)

Max Activating Token Index: 658

Text #10

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2723. Min Act: -0.0000

Data Index: 105926 (The Pile)

Max Activating Token Index: 576

Text #11

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2519. Min Act: -0.0000

Data Index: 829769 (The Pile)

Max Activating Token Index: 709

Text #12

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2364. Min Act: -0.0000

Data Index: 550232 (The Pile)

Max Activating Token Index: 427

Text #13

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2198. Min Act: -0.0000

Data Index: 1789672 (The Pile)

Max Activating Token Index: 686

Text #14

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2402. Min Act: -0.0000

Data Index: 1486562 (The Pile)

Max Activating Token Index: 157

Text #15

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2431. Min Act: -0.0000

Data Index: 264469 (The Pile)

Max Activating Token Index: 222

Text #16

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2826. Min Act: -0.0000

Data Index: 1417280 (The Pile)

Max Activating Token Index: 507

Text #17

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2307. Min Act: -0.0000

Data Index: 825384 (The Pile)

Max Activating Token Index: 280

Text #18

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2387. Min Act: -0.0000

Data Index: 1295307 (The Pile)

Max Activating Token Index: 452

Text #19

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2105. Min Act: -0.0000

Data Index: 1841852 (The Pile)

Max Activating Token Index: 97