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

Dataset: The Pile

Neuron 4030 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: 1.6864. Min Range: -1.6864

Max Act: 1.6864. Min Act: -0.0000

Data Index: 1389178 (The Pile)

Max Activating Token Index: 244

Text #1

Max Range: 1.6864. Min Range: -1.6864

Max Act: 1.5505. Min Act: -0.0000

Data Index: 59378 (The Pile)

Max Activating Token Index: 31

Text #2

Max Range: 1.6864. Min Range: -1.6864

Max Act: 1.4720. Min Act: -0.0000

Data Index: 910954 (The Pile)

Max Activating Token Index: 122

Text #3

Max Range: 1.6864. Min Range: -1.6864

Max Act: 1.4441. Min Act: -0.0000

Data Index: 1944053 (The Pile)

Max Activating Token Index: 40

Text #4

Max Range: 1.6864. Min Range: -1.6864

Max Act: 1.3753. Min Act: -0.0000

Data Index: 1170407 (The Pile)

Max Activating Token Index: 251

Text #5

Max Range: 1.6864. Min Range: -1.6864

Max Act: 1.2202. Min Act: -0.0000

Data Index: 1641796 (The Pile)

Max Activating Token Index: 978

Text #6

Max Range: 1.6864. Min Range: -1.6864

Max Act: 1.1349. Min Act: -0.0000

Data Index: 1369168 (The Pile)

Max Activating Token Index: 727

Text #7

Max Range: 1.6864. Min Range: -1.6864

Max Act: 1.1242. Min Act: -0.0000

Data Index: 1906281 (The Pile)

Max Activating Token Index: 26

Text #8

Max Range: 1.6864. Min Range: -1.6864

Max Act: 1.0530. Min Act: -0.0000

Data Index: 1739964 (The Pile)

Max Activating Token Index: 200

Text #9

Max Range: 1.6864. Min Range: -1.6864

Max Act: 0.9990. Min Act: -0.0000

Data Index: 937016 (The Pile)

Max Activating Token Index: 897

Text #10

Max Range: 1.6864. Min Range: -1.6864

Max Act: 0.9503. Min Act: -0.0000

Data Index: 363827 (The Pile)

Max Activating Token Index: 596

Text #11

Max Range: 1.6864. Min Range: -1.6864

Max Act: 0.9481. Min Act: -0.0000

Data Index: 1676798 (The Pile)

Max Activating Token Index: 712

Text #12

Max Range: 1.6864. Min Range: -1.6864

Max Act: 0.9430. Min Act: -0.0000

Data Index: 1875757 (The Pile)

Max Activating Token Index: 961

Text #13

Max Range: 1.6864. Min Range: -1.6864

Max Act: 1.0599. Min Act: -0.0000

Data Index: 1648778 (The Pile)

Max Activating Token Index: 600

Text #14

Max Range: 1.6864. Min Range: -1.6864

Max Act: 0.9589. Min Act: -0.0000

Data Index: 1159835 (The Pile)

Max Activating Token Index: 54

Text #15

Max Range: 1.6864. Min Range: -1.6864

Max Act: 0.8975. Min Act: -0.0000

Data Index: 1777136 (The Pile)

Max Activating Token Index: 844

Text #16

Max Range: 1.6864. Min Range: -1.6864

Max Act: 0.8490. Min Act: -0.0000

Data Index: 938456 (The Pile)

Max Activating Token Index: 693

Text #17

Max Range: 1.6864. Min Range: -1.6864

Max Act: 0.9105. Min Act: -0.0000

Data Index: 1092226 (The Pile)

Max Activating Token Index: 879

Text #18

Max Range: 1.6864. Min Range: -1.6864

Max Act: 0.8782. Min Act: -0.0000

Data Index: 1242321 (The Pile)

Max Activating Token Index: 182

Text #19

Max Range: 1.6864. Min Range: -1.6864

Max Act: 0.8950. Min Act: -0.0000

Data Index: 214504 (The Pile)

Max Activating Token Index: 173