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

Dataset: The Pile

Neuron 3557 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: 3.8030. Min Range: -3.8030

Max Act: 3.8030. Min Act: -0.0000

Data Index: 1559448 (The Pile)

Max Activating Token Index: 201

Text #1

Max Range: 3.8030. Min Range: -3.8030

Max Act: 3.6626. Min Act: 0.0000

Data Index: 679027 (The Pile)

Max Activating Token Index: 302

Text #2

Max Range: 3.8030. Min Range: -3.8030

Max Act: 3.5115. Min Act: -0.0000

Data Index: 947365 (The Pile)

Max Activating Token Index: 520

Text #3

Max Range: 3.8030. Min Range: -3.8030

Max Act: 3.2052. Min Act: -0.0000

Data Index: 1338975 (The Pile)

Max Activating Token Index: 575

Text #4

Max Range: 3.8030. Min Range: -3.8030

Max Act: 3.0712. Min Act: 0.0000

Data Index: 1431414 (The Pile)

Max Activating Token Index: 402

Text #5

Max Range: 3.8030. Min Range: -3.8030

Max Act: 3.0135. Min Act: -0.0000

Data Index: 178091 (The Pile)

Max Activating Token Index: 660

Text #6

Max Range: 3.8030. Min Range: -3.8030

Max Act: 3.0449. Min Act: 0.0000

Data Index: 1860087 (The Pile)

Max Activating Token Index: 187

Text #7

Max Range: 3.8030. Min Range: -3.8030

Max Act: 3.2164. Min Act: -0.0000

Data Index: 963115 (The Pile)

Max Activating Token Index: 772

Text #8

Max Range: 3.8030. Min Range: -3.8030

Max Act: 2.8614. Min Act: -0.0000

Data Index: 1142953 (The Pile)

Max Activating Token Index: 340

Text #9

Max Range: 3.8030. Min Range: -3.8030

Max Act: 2.8814. Min Act: -0.0000

Data Index: 1010573 (The Pile)

Max Activating Token Index: 660

Text #10

Max Range: 3.8030. Min Range: -3.8030

Max Act: 2.9207. Min Act: -0.0000

Data Index: 1857924 (The Pile)

Max Activating Token Index: 700

Text #11

Max Range: 3.8030. Min Range: -3.8030

Max Act: 2.6892. Min Act: -0.0000

Data Index: 1546656 (The Pile)

Max Activating Token Index: 680

Text #12

Max Range: 3.8030. Min Range: -3.8030

Max Act: 2.8214. Min Act: -0.0000

Data Index: 1682721 (The Pile)

Max Activating Token Index: 79

Text #13

Max Range: 3.8030. Min Range: -3.8030

Max Act: 2.9279. Min Act: -0.0000

Data Index: 997862 (The Pile)

Max Activating Token Index: 686

Text #14

Max Range: 3.8030. Min Range: -3.8030

Max Act: 2.6078. Min Act: -0.0000

Data Index: 1114866 (The Pile)

Max Activating Token Index: 195

Text #15

Max Range: 3.8030. Min Range: -3.8030

Max Act: 2.7035. Min Act: -0.0000

Data Index: 895694 (The Pile)

Max Activating Token Index: 406

Text #16

Max Range: 3.8030. Min Range: -3.8030

Max Act: 2.7286. Min Act: -0.0000

Data Index: 1383742 (The Pile)

Max Activating Token Index: 490

Text #17

Max Range: 3.8030. Min Range: -3.8030

Max Act: 2.8141. Min Act: -0.0000

Data Index: 1466748 (The Pile)

Max Activating Token Index: 625

Text #18

Max Range: 3.8030. Min Range: -3.8030

Max Act: 2.5684. Min Act: -0.0000

Data Index: 1649323 (The Pile)

Max Activating Token Index: 137

Text #19

Max Range: 3.8030. Min Range: -3.8030

Max Act: 2.6676. Min Act: -0.0000

Data Index: 1782267 (The Pile)

Max Activating Token Index: 229