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

Dataset: The Pile

Neuron 3301 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8012. Min Range: -2.8012

Max Act: 2.8012. Min Act: -0.0000

Data Index: 536658 (The Pile)

Max Activating Token Index: 527

Text #1

Max Range: 2.8012. Min Range: -2.8012

Max Act: 2.1409. Min Act: -0.0000

Data Index: 1761759 (The Pile)

Max Activating Token Index: 395

Text #2

Max Range: 2.8012. Min Range: -2.8012

Max Act: 1.7146. Min Act: -0.0000

Data Index: 726933 (The Pile)

Max Activating Token Index: 238

Text #3

Max Range: 2.8012. Min Range: -2.8012

Max Act: 1.9319. Min Act: -0.0000

Data Index: 1525572 (The Pile)

Max Activating Token Index: 312

Text #4

Max Range: 2.8012. Min Range: -2.8012

Max Act: 1.8996. Min Act: -0.0000

Data Index: 1948816 (The Pile)

Max Activating Token Index: 725

Text #5

Max Range: 2.8012. Min Range: -2.8012

Max Act: 1.8516. Min Act: -0.0000

Data Index: 1047405 (The Pile)

Max Activating Token Index: 162

Text #6

Max Range: 2.8012. Min Range: -2.8012

Max Act: 2.0390. Min Act: -0.0000

Data Index: 172980 (The Pile)

Max Activating Token Index: 54

Text #7

Max Range: 2.8012. Min Range: -2.8012

Max Act: 1.8951. Min Act: -0.0000

Data Index: 1327837 (The Pile)

Max Activating Token Index: 179

Text #8

Max Range: 2.8012. Min Range: -2.8012

Max Act: 1.7828. Min Act: -0.0000

Data Index: 1452983 (The Pile)

Max Activating Token Index: 649

Text #9

Max Range: 2.8012. Min Range: -2.8012

Max Act: 1.8497. Min Act: -0.0000

Data Index: 170114 (The Pile)

Max Activating Token Index: 1019

Text #10

Max Range: 2.8012. Min Range: -2.8012

Max Act: 1.5647. Min Act: -0.0000

Data Index: 1619249 (The Pile)

Max Activating Token Index: 319

Text #11

Max Range: 2.8012. Min Range: -2.8012

Max Act: 1.6555. Min Act: -0.0000

Data Index: 651454 (The Pile)

Max Activating Token Index: 953

Text #12

Max Range: 2.8012. Min Range: -2.8012

Max Act: 1.5821. Min Act: -0.0000

Data Index: 1558406 (The Pile)

Max Activating Token Index: 759

Text #13

Max Range: 2.8012. Min Range: -2.8012

Max Act: 1.0851. Min Act: -0.0000

Data Index: 1199501 (The Pile)

Max Activating Token Index: 72

Text #14

Max Range: 2.8012. Min Range: -2.8012

Max Act: 1.5260. Min Act: -0.0000

Data Index: 60598 (The Pile)

Max Activating Token Index: 901

Text #15

Max Range: 2.8012. Min Range: -2.8012

Max Act: 1.7773. Min Act: -0.0000

Data Index: 1878295 (The Pile)

Max Activating Token Index: 543

Text #16

Max Range: 2.8012. Min Range: -2.8012

Max Act: 1.5973. Min Act: -0.0000

Data Index: 389693 (The Pile)

Max Activating Token Index: 645

Text #17

Max Range: 2.8012. Min Range: -2.8012

Max Act: 1.6579. Min Act: -0.0000

Data Index: 1444820 (The Pile)

Max Activating Token Index: 154

Text #18

Max Range: 2.8012. Min Range: -2.8012

Max Act: 1.5662. Min Act: -0.0000

Data Index: 1490830 (The Pile)

Max Activating Token Index: 415

Text #19

Max Range: 2.8012. Min Range: -2.8012

Max Act: 1.6740. Min Act: -0.0000

Data Index: 962305 (The Pile)

Max Activating Token Index: 863