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

Dataset: The Pile

Neuron 2434 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: 3.2876. Min Range: -3.2876

Max Act: 3.2876. Min Act: -0.0000

Data Index: 1110592 (The Pile)

Max Activating Token Index: 138

Text #1

Max Range: 3.2876. Min Range: -3.2876

Max Act: 3.1601. Min Act: -0.0000

Data Index: 1437864 (The Pile)

Max Activating Token Index: 676

Text #2

Max Range: 3.2876. Min Range: -3.2876

Max Act: 3.2341. Min Act: -0.0000

Data Index: 176349 (The Pile)

Max Activating Token Index: 447

Text #3

Max Range: 3.2876. Min Range: -3.2876

Max Act: 3.1516. Min Act: -0.0000

Data Index: 1929088 (The Pile)

Max Activating Token Index: 810

Text #4

Max Range: 3.2876. Min Range: -3.2876

Max Act: 3.2515. Min Act: -0.0000

Data Index: 1484681 (The Pile)

Max Activating Token Index: 2

Text #5

Max Range: 3.2876. Min Range: -3.2876

Max Act: 3.2515. Min Act: 0.0000

Data Index: 1449372 (The Pile)

Max Activating Token Index: 2

Text #6

Max Range: 3.2876. Min Range: -3.2876

Max Act: 3.2171. Min Act: -0.0000

Data Index: 1473709 (The Pile)

Max Activating Token Index: 59

Text #7

Max Range: 3.2876. Min Range: -3.2876

Max Act: 3.0179. Min Act: -0.0000

Data Index: 1932287 (The Pile)

Max Activating Token Index: 468

Text #8

Max Range: 3.2876. Min Range: -3.2876

Max Act: 2.9721. Min Act: -0.0000

Data Index: 1074697 (The Pile)

Max Activating Token Index: 410

Text #9

Max Range: 3.2876. Min Range: -3.2876

Max Act: 2.5778. Min Act: -0.0000

Data Index: 752817 (The Pile)

Max Activating Token Index: 225

Text #10

Max Range: 3.2876. Min Range: -3.2876

Max Act: 3.0059. Min Act: -0.0000

Data Index: 112618 (The Pile)

Max Activating Token Index: 864

Text #11

Max Range: 3.2876. Min Range: -3.2876

Max Act: 2.8176. Min Act: -0.0000

Data Index: 1413178 (The Pile)

Max Activating Token Index: 502

Text #12

Max Range: 3.2876. Min Range: -3.2876

Max Act: 2.6769. Min Act: -0.0000

Data Index: 273392 (The Pile)

Max Activating Token Index: 240

Text #13

Max Range: 3.2876. Min Range: -3.2876

Max Act: 2.9026. Min Act: -0.0000

Data Index: 1483275 (The Pile)

Max Activating Token Index: 564

Text #14

Max Range: 3.2876. Min Range: -3.2876

Max Act: 2.7921. Min Act: -0.0000

Data Index: 1694243 (The Pile)

Max Activating Token Index: 870

Text #15

Max Range: 3.2876. Min Range: -3.2876

Max Act: 2.9273. Min Act: -0.0000

Data Index: 259137 (The Pile)

Max Activating Token Index: 953

Text #16

Max Range: 3.2876. Min Range: -3.2876

Max Act: 2.7720. Min Act: -0.0000

Data Index: 1480308 (The Pile)

Max Activating Token Index: 925

Text #17

Max Range: 3.2876. Min Range: -3.2876

Max Act: 2.8955. Min Act: -0.0000

Data Index: 15641 (The Pile)

Max Activating Token Index: 132

Text #18

Max Range: 3.2876. Min Range: -3.2876

Max Act: 2.8656. Min Act: -0.0000

Data Index: 880529 (The Pile)

Max Activating Token Index: 257

Text #19

Max Range: 3.2876. Min Range: -3.2876

Max Act: 2.8563. Min Act: -0.0000

Data Index: 232859 (The Pile)

Max Activating Token Index: 15