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

Dataset: The Pile

Neuron 4510 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: 0.7847. Min Range: -0.7847

Max Act: 0.7847. Min Act: -0.0000

Data Index: 1718360 (The Pile)

Max Activating Token Index: 854

Text #1

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.6137. Min Act: -0.0000

Data Index: 1737626 (The Pile)

Max Activating Token Index: 326

Text #2

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.5677. Min Act: -0.0000

Data Index: 1560337 (The Pile)

Max Activating Token Index: 13

Text #3

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.5514. Min Act: -0.0000

Data Index: 163363 (The Pile)

Max Activating Token Index: 894

Text #4

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.5312. Min Act: -0.0000

Data Index: 1428382 (The Pile)

Max Activating Token Index: 778

Text #5

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.5459. Min Act: -0.0000

Data Index: 1690241 (The Pile)

Max Activating Token Index: 696

Text #6

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.5136. Min Act: -0.0000

Data Index: 1002721 (The Pile)

Max Activating Token Index: 958

Text #7

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.5138. Min Act: -0.0000

Data Index: 1734193 (The Pile)

Max Activating Token Index: 717

Text #8

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.4841. Min Act: -0.0000

Data Index: 902747 (The Pile)

Max Activating Token Index: 346

Text #9

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.4837. Min Act: -0.0000

Data Index: 885718 (The Pile)

Max Activating Token Index: 452

Text #10

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.4534. Min Act: -0.0000

Data Index: 474884 (The Pile)

Max Activating Token Index: 647

Text #11

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.4544. Min Act: -0.0000

Data Index: 608859 (The Pile)

Max Activating Token Index: 535

Text #12

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.4555. Min Act: -0.0000

Data Index: 1677687 (The Pile)

Max Activating Token Index: 742

Text #13

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.4158. Min Act: -0.0000

Data Index: 261866 (The Pile)

Max Activating Token Index: 350

Text #14

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.4123. Min Act: 0.0000

Data Index: 1487066 (The Pile)

Max Activating Token Index: 191

Text #15

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.4022. Min Act: -0.0000

Data Index: 1017523 (The Pile)

Max Activating Token Index: 933

Text #16

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.4163. Min Act: -0.0000

Data Index: 228175 (The Pile)

Max Activating Token Index: 698

Text #17

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.4090. Min Act: -0.0000

Data Index: 500328 (The Pile)

Max Activating Token Index: 634

Text #18

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.4090. Min Act: -0.0000

Data Index: 1847723 (The Pile)

Max Activating Token Index: 588

Text #19

Max Range: 0.7847. Min Range: -0.7847

Max Act: 0.3816. Min Act: -0.0000

Data Index: 1807636 (The Pile)

Max Activating Token Index: 632