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

Dataset: The Pile

Neuron 2881 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8503. Min Range: -1.8503

Max Act: 1.8503. Min Act: -0.0000

Data Index: 1156801 (The Pile)

Max Activating Token Index: 567

Text #1

Max Range: 1.8503. Min Range: -1.8503

Max Act: 1.7442. Min Act: -0.0000

Data Index: 1939357 (The Pile)

Max Activating Token Index: 996

Text #2

Max Range: 1.8503. Min Range: -1.8503

Max Act: 1.5641. Min Act: -0.0000

Data Index: 306540 (The Pile)

Max Activating Token Index: 78

Text #3

Max Range: 1.8503. Min Range: -1.8503

Max Act: 1.4496. Min Act: -0.0000

Data Index: 1181529 (The Pile)

Max Activating Token Index: 293

Text #4

Max Range: 1.8503. Min Range: -1.8503

Max Act: 1.5553. Min Act: -0.0000

Data Index: 1187124 (The Pile)

Max Activating Token Index: 526

Text #5

Max Range: 1.8503. Min Range: -1.8503

Max Act: 1.6377. Min Act: -0.0000

Data Index: 715046 (The Pile)

Max Activating Token Index: 672

Text #6

Max Range: 1.8503. Min Range: -1.8503

Max Act: 1.5449. Min Act: -0.0000

Data Index: 1836968 (The Pile)

Max Activating Token Index: 83

Text #7

Max Range: 1.8503. Min Range: -1.8503

Max Act: 1.4593. Min Act: -0.0000

Data Index: 240328 (The Pile)

Max Activating Token Index: 739

Text #8

Max Range: 1.8503. Min Range: -1.8503

Max Act: 1.4521. Min Act: -0.0000

Data Index: 1156436 (The Pile)

Max Activating Token Index: 512

Text #9

Max Range: 1.8503. Min Range: -1.8503

Max Act: 1.4010. Min Act: -0.0000

Data Index: 1514947 (The Pile)

Max Activating Token Index: 595

Text #10

Max Range: 1.8503. Min Range: -1.8503

Max Act: 1.4321. Min Act: -0.0000

Data Index: 1914782 (The Pile)

Max Activating Token Index: 457

Text #11

Max Range: 1.8503. Min Range: -1.8503

Max Act: 1.4850. Min Act: -0.0000

Data Index: 119756 (The Pile)

Max Activating Token Index: 810

Text #12

Max Range: 1.8503. Min Range: -1.8503

Max Act: 1.4516. Min Act: -0.0000

Data Index: 1397325 (The Pile)

Max Activating Token Index: 939

Text #13

Max Range: 1.8503. Min Range: -1.8503

Max Act: 1.2976. Min Act: -0.0000

Data Index: 1970543 (The Pile)

Max Activating Token Index: 352

Text #14

Max Range: 1.8503. Min Range: -1.8503

Max Act: 1.4516. Min Act: -0.0000

Data Index: 842402 (The Pile)

Max Activating Token Index: 265

Text #15

Max Range: 1.8503. Min Range: -1.8503

Max Act: 1.4860. Min Act: -0.0000

Data Index: 1058468 (The Pile)

Max Activating Token Index: 859

Text #16

Max Range: 1.8503. Min Range: -1.8503

Max Act: 1.3564. Min Act: -0.0000

Data Index: 617141 (The Pile)

Max Activating Token Index: 315

Text #17

Max Range: 1.8503. Min Range: -1.8503

Max Act: 1.3309. Min Act: -0.0000

Data Index: 743729 (The Pile)

Max Activating Token Index: 234

Text #18

Max Range: 1.8503. Min Range: -1.8503

Max Act: 1.2822. Min Act: -0.0000

Data Index: 1311208 (The Pile)

Max Activating Token Index: 798

Text #19

Max Range: 1.8503. Min Range: -1.8503

Max Act: 1.3417. Min Act: -0.0000

Data Index: 1639003 (The Pile)

Max Activating Token Index: 784