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

Dataset: The Pile

Neuron 434 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: 1.0532. Min Range: -1.0532

Max Act: 1.0532. Min Act: -0.0000

Data Index: 1765817 (The Pile)

Max Activating Token Index: 618

Text #1

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.9892. Min Act: -0.0000

Data Index: 308286 (The Pile)

Max Activating Token Index: 933

Text #2

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.7871. Min Act: -0.0000

Data Index: 71313 (The Pile)

Max Activating Token Index: 287

Text #3

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.9172. Min Act: -0.0000

Data Index: 824061 (The Pile)

Max Activating Token Index: 725

Text #4

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.7287. Min Act: -0.0000

Data Index: 257005 (The Pile)

Max Activating Token Index: 989

Text #5

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.7034. Min Act: -0.0000

Data Index: 1947183 (The Pile)

Max Activating Token Index: 791

Text #6

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.7017. Min Act: -0.0000

Data Index: 1531263 (The Pile)

Max Activating Token Index: 737

Text #7

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.7452. Min Act: -0.0000

Data Index: 1449948 (The Pile)

Max Activating Token Index: 428

Text #8

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.7366. Min Act: -0.0000

Data Index: 997170 (The Pile)

Max Activating Token Index: 663

Text #9

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.7331. Min Act: -0.0000

Data Index: 962483 (The Pile)

Max Activating Token Index: 139

Text #10

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.7362. Min Act: -0.0000

Data Index: 171944 (The Pile)

Max Activating Token Index: 287

Text #11

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.7239. Min Act: -0.0000

Data Index: 1762975 (The Pile)

Max Activating Token Index: 118

Text #12

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.6518. Min Act: -0.0000

Data Index: 454316 (The Pile)

Max Activating Token Index: 834

Text #13

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.7049. Min Act: -0.0000

Data Index: 1030465 (The Pile)

Max Activating Token Index: 341

Text #14

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.6913. Min Act: -0.0000

Data Index: 1555903 (The Pile)

Max Activating Token Index: 957

Text #15

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.6367. Min Act: -0.0000

Data Index: 513902 (The Pile)

Max Activating Token Index: 143

Text #16

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.6880. Min Act: -0.0000

Data Index: 131684 (The Pile)

Max Activating Token Index: 1005

Text #17

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.6292. Min Act: -0.0000

Data Index: 1876388 (The Pile)

Max Activating Token Index: 313

Text #18

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.6636. Min Act: -0.0000

Data Index: 179401 (The Pile)

Max Activating Token Index: 152

Text #19

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.6220. Min Act: -0.0000

Data Index: 210829 (The Pile)

Max Activating Token Index: 114