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

Dataset: The Pile

Neuron 1399 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: 0.5947. Min Range: -0.5947

Max Act: 0.5947. Min Act: -0.0000

Data Index: 727117 (The Pile)

Max Activating Token Index: 193

Text #1

Max Range: 0.5947. Min Range: -0.5947

Max Act: 0.5769. Min Act: -0.0000

Data Index: 1821539 (The Pile)

Max Activating Token Index: 604

Text #2

Max Range: 0.5947. Min Range: -0.5947

Max Act: 0.5248. Min Act: -0.0000

Data Index: 1512155 (The Pile)

Max Activating Token Index: 413

Text #3

Max Range: 0.5947. Min Range: -0.5947

Max Act: 0.4677. Min Act: -0.0000

Data Index: 901018 (The Pile)

Max Activating Token Index: 855

Text #4

Max Range: 0.5947. Min Range: -0.5947

Max Act: 0.4528. Min Act: -0.0000

Data Index: 139535 (The Pile)

Max Activating Token Index: 188

Text #5

Max Range: 0.5947. Min Range: -0.5947

Max Act: 0.4366. Min Act: -0.0000

Data Index: 992174 (The Pile)

Max Activating Token Index: 209

Text #6

Max Range: 0.5947. Min Range: -0.5947

Max Act: 0.4073. Min Act: -0.0000

Data Index: 1118451 (The Pile)

Max Activating Token Index: 474

Text #7

Max Range: 0.5947. Min Range: -0.5947

Max Act: 0.4380. Min Act: -0.0000

Data Index: 1413363 (The Pile)

Max Activating Token Index: 293

Text #8

Max Range: 0.5947. Min Range: -0.5947

Max Act: 0.4232. Min Act: -0.0000

Data Index: 1691625 (The Pile)

Max Activating Token Index: 440

Text #9

Max Range: 0.5947. Min Range: -0.5947

Max Act: 0.4016. Min Act: -0.0000

Data Index: 1753927 (The Pile)

Max Activating Token Index: 731

Text #10

Max Range: 0.5947. Min Range: -0.5947

Max Act: 0.5098. Min Act: -0.0000

Data Index: 1542845 (The Pile)

Max Activating Token Index: 366

Text #11

Max Range: 0.5947. Min Range: -0.5947

Max Act: 0.4016. Min Act: -0.0000

Data Index: 1742465 (The Pile)

Max Activating Token Index: 386

Text #12

Max Range: 0.5947. Min Range: -0.5947

Max Act: 0.4522. Min Act: -0.0000

Data Index: 1057155 (The Pile)

Max Activating Token Index: 992

Text #13

Max Range: 0.5947. Min Range: -0.5947

Max Act: 0.4390. Min Act: -0.0000

Data Index: 865776 (The Pile)

Max Activating Token Index: 839

Text #14

Max Range: 0.5947. Min Range: -0.5947

Max Act: 0.4398. Min Act: -0.0000

Data Index: 729240 (The Pile)

Max Activating Token Index: 694

Text #15

Max Range: 0.5947. Min Range: -0.5947

Max Act: 0.4113. Min Act: -0.0000

Data Index: 1896410 (The Pile)

Max Activating Token Index: 170

Text #16

Max Range: 0.5947. Min Range: -0.5947

Max Act: 0.4381. Min Act: -0.0000

Data Index: 1038195 (The Pile)

Max Activating Token Index: 123

Text #17

Max Range: 0.5947. Min Range: -0.5947

Max Act: 0.4456. Min Act: -0.0000

Data Index: 1381058 (The Pile)

Max Activating Token Index: 744

Text #18

Max Range: 0.5947. Min Range: -0.5947

Max Act: 0.4499. Min Act: -0.0000

Data Index: 467296 (The Pile)

Max Activating Token Index: 659

Text #19

Max Range: 0.5947. Min Range: -0.5947

Max Act: 0.4132. Min Act: -0.0000

Data Index: 1292563 (The Pile)

Max Activating Token Index: 885