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

Dataset: The Pile

Neuron 2501 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0506. Min Range: -1.0506

Max Act: 1.0506. Min Act: -0.0000

Data Index: 883807 (The Pile)

Max Activating Token Index: 663

Text #1

Max Range: 1.0506. Min Range: -1.0506

Max Act: 1.0108. Min Act: -0.0000

Data Index: 246208 (The Pile)

Max Activating Token Index: 248

Text #2

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.9911. Min Act: -0.0000

Data Index: 1242776 (The Pile)

Max Activating Token Index: 235

Text #3

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.9916. Min Act: -0.0000

Data Index: 1314241 (The Pile)

Max Activating Token Index: 208

Text #4

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.9242. Min Act: -0.0000

Data Index: 224200 (The Pile)

Max Activating Token Index: 686

Text #5

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.9322. Min Act: -0.0000

Data Index: 1710984 (The Pile)

Max Activating Token Index: 553

Text #6

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.9326. Min Act: -0.0000

Data Index: 1365089 (The Pile)

Max Activating Token Index: 171

Text #7

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.9041. Min Act: -0.0000

Data Index: 953310 (The Pile)

Max Activating Token Index: 519

Text #8

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.9498. Min Act: -0.0000

Data Index: 1622636 (The Pile)

Max Activating Token Index: 914

Text #9

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.9166. Min Act: -0.0000

Data Index: 809842 (The Pile)

Max Activating Token Index: 150

Text #10

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.8863. Min Act: -0.0000

Data Index: 1046184 (The Pile)

Max Activating Token Index: 531

Text #11

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.8665. Min Act: -0.0000

Data Index: 1120081 (The Pile)

Max Activating Token Index: 335

Text #12

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.8140. Min Act: -0.0000

Data Index: 1254002 (The Pile)

Max Activating Token Index: 103

Text #13

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.8331. Min Act: -0.0000

Data Index: 675075 (The Pile)

Max Activating Token Index: 741

Text #14

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.8570. Min Act: -0.0000

Data Index: 1706156 (The Pile)

Max Activating Token Index: 486

Text #15

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.8277. Min Act: -0.0000

Data Index: 1575735 (The Pile)

Max Activating Token Index: 823

Text #16

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.7898. Min Act: -0.0000

Data Index: 966900 (The Pile)

Max Activating Token Index: 674

Text #17

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.8154. Min Act: -0.0000

Data Index: 1864456 (The Pile)

Max Activating Token Index: 303

Text #18

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.8157. Min Act: -0.0000

Data Index: 621741 (The Pile)

Max Activating Token Index: 104

Text #19

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.8098. Min Act: -0.0000

Data Index: 399620 (The Pile)

Max Activating Token Index: 103