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

Dataset: The Pile

Neuron 3271 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: 0.7589. Min Range: -0.7589

Max Act: 0.7589. Min Act: -0.0000

Data Index: 677971 (The Pile)

Max Activating Token Index: 978

Text #1

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.7279. Min Act: -0.0000

Data Index: 1214375 (The Pile)

Max Activating Token Index: 351

Text #2

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.7163. Min Act: -0.0000

Data Index: 301177 (The Pile)

Max Activating Token Index: 360

Text #3

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.6383. Min Act: -0.0000

Data Index: 181332 (The Pile)

Max Activating Token Index: 586

Text #4

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.6815. Min Act: -0.0000

Data Index: 913833 (The Pile)

Max Activating Token Index: 738

Text #5

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.6955. Min Act: -0.0000

Data Index: 1932288 (The Pile)

Max Activating Token Index: 247

Text #6

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.6722. Min Act: -0.0000

Data Index: 926 (The Pile)

Max Activating Token Index: 458

Text #7

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.6719. Min Act: -0.0000

Data Index: 834121 (The Pile)

Max Activating Token Index: 233

Text #8

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.6474. Min Act: -0.0000

Data Index: 430418 (The Pile)

Max Activating Token Index: 270

Text #9

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.6344. Min Act: -0.0000

Data Index: 821775 (The Pile)

Max Activating Token Index: 87

Text #10

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.7127. Min Act: -0.0000

Data Index: 148447 (The Pile)

Max Activating Token Index: 138

Text #11

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.6487. Min Act: -0.0000

Data Index: 1931732 (The Pile)

Max Activating Token Index: 293

Text #12

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.6116. Min Act: -0.0000

Data Index: 875496 (The Pile)

Max Activating Token Index: 223

Text #13

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.6537. Min Act: -0.0000

Data Index: 1292165 (The Pile)

Max Activating Token Index: 531

Text #14

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.5948. Min Act: -0.0000

Data Index: 1332070 (The Pile)

Max Activating Token Index: 527

Text #15

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.6044. Min Act: -0.0000

Data Index: 1315455 (The Pile)

Max Activating Token Index: 845

Text #16

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.6378. Min Act: -0.0000

Data Index: 1941668 (The Pile)

Max Activating Token Index: 899

Text #17

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.6140. Min Act: -0.0000

Data Index: 1524706 (The Pile)

Max Activating Token Index: 385

Text #18

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.6099. Min Act: -0.0000

Data Index: 367987 (The Pile)

Max Activating Token Index: 292

Text #19

Max Range: 0.7589. Min Range: -0.7589

Max Act: 0.5751. Min Act: -0.0000

Data Index: 693948 (The Pile)

Max Activating Token Index: 683