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

Dataset: The Pile

Neuron 1447 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: 1.9083. Min Range: -1.9083

Max Act: 1.9083. Min Act: -0.0000

Data Index: 1204885 (The Pile)

Max Activating Token Index: 202

Text #1

Max Range: 1.9083. Min Range: -1.9083

Max Act: 1.3211. Min Act: -0.0000

Data Index: 1024929 (The Pile)

Max Activating Token Index: 217

Text #2

Max Range: 1.9083. Min Range: -1.9083

Max Act: 1.3431. Min Act: -0.0000

Data Index: 1917274 (The Pile)

Max Activating Token Index: 492

Text #3

Max Range: 1.9083. Min Range: -1.9083

Max Act: 1.2855. Min Act: -0.0000

Data Index: 1749163 (The Pile)

Max Activating Token Index: 803

Text #4

Max Range: 1.9083. Min Range: -1.9083

Max Act: 1.2384. Min Act: -0.0000

Data Index: 1551209 (The Pile)

Max Activating Token Index: 813

Text #5

Max Range: 1.9083. Min Range: -1.9083

Max Act: 1.2084. Min Act: -0.0000

Data Index: 38284 (The Pile)

Max Activating Token Index: 1022

Text #6

Max Range: 1.9083. Min Range: -1.9083

Max Act: 1.2318. Min Act: -0.0000

Data Index: 341722 (The Pile)

Max Activating Token Index: 526

Text #7

Max Range: 1.9083. Min Range: -1.9083

Max Act: 1.1243. Min Act: -0.0000

Data Index: 27210 (The Pile)

Max Activating Token Index: 954

Text #8

Max Range: 1.9083. Min Range: -1.9083

Max Act: 1.0756. Min Act: -0.0000

Data Index: 1470550 (The Pile)

Max Activating Token Index: 667

Text #9

Max Range: 1.9083. Min Range: -1.9083

Max Act: 1.1431. Min Act: -0.0000

Data Index: 742144 (The Pile)

Max Activating Token Index: 299

Text #10

Max Range: 1.9083. Min Range: -1.9083

Max Act: 1.1025. Min Act: -0.0000

Data Index: 1532752 (The Pile)

Max Activating Token Index: 859

Text #11

Max Range: 1.9083. Min Range: -1.9083

Max Act: 1.0536. Min Act: -0.0000

Data Index: 1324222 (The Pile)

Max Activating Token Index: 989

Text #12

Max Range: 1.9083. Min Range: -1.9083

Max Act: 1.1634. Min Act: -0.0000

Data Index: 121254 (The Pile)

Max Activating Token Index: 874

Text #13

Max Range: 1.9083. Min Range: -1.9083

Max Act: 1.0826. Min Act: -0.0000

Data Index: 1955035 (The Pile)

Max Activating Token Index: 198

Text #14

Max Range: 1.9083. Min Range: -1.9083

Max Act: 1.1192. Min Act: -0.0000

Data Index: 482811 (The Pile)

Max Activating Token Index: 165

Text #15

Max Range: 1.9083. Min Range: -1.9083

Max Act: 1.0383. Min Act: -0.0000

Data Index: 1799961 (The Pile)

Max Activating Token Index: 112

Text #16

Max Range: 1.9083. Min Range: -1.9083

Max Act: 1.0331. Min Act: -0.0000

Data Index: 1789062 (The Pile)

Max Activating Token Index: 844

Text #17

Max Range: 1.9083. Min Range: -1.9083

Max Act: 0.9719. Min Act: -0.0000

Data Index: 1768200 (The Pile)

Max Activating Token Index: 807

Text #18

Max Range: 1.9083. Min Range: -1.9083

Max Act: 0.9518. Min Act: -0.0000

Data Index: 1194879 (The Pile)

Max Activating Token Index: 616

Text #19

Max Range: 1.9083. Min Range: -1.9083

Max Act: 1.0204. Min Act: -0.0000

Data Index: 1939653 (The Pile)

Max Activating Token Index: 377