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

Dataset: The Pile

Neuron 1108 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: 1.1125. Min Range: -1.1125

Max Act: 1.1024. Min Act: -0.0000

Data Index: 1406269 (The Pile)

Max Activating Token Index: 425

Text #1

Max Range: 1.1125. Min Range: -1.1125

Max Act: 1.0664. Min Act: -0.0000

Data Index: 1918214 (The Pile)

Max Activating Token Index: 211

Text #2

Max Range: 1.1125. Min Range: -1.1125

Max Act: 1.0761. Min Act: -0.0000

Data Index: 1155121 (The Pile)

Max Activating Token Index: 192

Text #3

Max Range: 1.1125. Min Range: -1.1125

Max Act: 1.1125. Min Act: -0.0000

Data Index: 1243729 (The Pile)

Max Activating Token Index: 809

Text #4

Max Range: 1.1125. Min Range: -1.1125

Max Act: 1.0550. Min Act: -0.0000

Data Index: 970445 (The Pile)

Max Activating Token Index: 898

Text #5

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.9734. Min Act: -0.0000

Data Index: 1053556 (The Pile)

Max Activating Token Index: 398

Text #6

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.9318. Min Act: -0.0000

Data Index: 1877080 (The Pile)

Max Activating Token Index: 421

Text #7

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.9038. Min Act: -0.0000

Data Index: 1642859 (The Pile)

Max Activating Token Index: 324

Text #8

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.9447. Min Act: -0.0000

Data Index: 407878 (The Pile)

Max Activating Token Index: 311

Text #9

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.9358. Min Act: -0.0000

Data Index: 975784 (The Pile)

Max Activating Token Index: 961

Text #10

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.9126. Min Act: -0.0000

Data Index: 1541231 (The Pile)

Max Activating Token Index: 641

Text #11

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.9119. Min Act: -0.0000

Data Index: 1500890 (The Pile)

Max Activating Token Index: 232

Text #12

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.8570. Min Act: -0.0000

Data Index: 1453731 (The Pile)

Max Activating Token Index: 971

Text #13

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.8742. Min Act: -0.0000

Data Index: 1186303 (The Pile)

Max Activating Token Index: 767

Text #14

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.8625. Min Act: -0.0000

Data Index: 1724194 (The Pile)

Max Activating Token Index: 122

Text #15

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.8113. Min Act: -0.0000

Data Index: 739294 (The Pile)

Max Activating Token Index: 268

Text #16

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.8196. Min Act: -0.0000

Data Index: 1963851 (The Pile)

Max Activating Token Index: 580

Text #17

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.7750. Min Act: -0.0000

Data Index: 111585 (The Pile)

Max Activating Token Index: 852

Text #18

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.7841. Min Act: -0.0000

Data Index: 1184619 (The Pile)

Max Activating Token Index: 650

Text #19

Max Range: 1.1125. Min Range: -1.1125

Max Act: 0.8230. Min Act: -0.0000

Data Index: 437684 (The Pile)

Max Activating Token Index: 74