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

Dataset: The Pile

Neuron 375 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2287. Min Range: -3.2287

Max Act: 3.0666. Min Act: -0.0000

Data Index: 1059727 (The Pile)

Max Activating Token Index: 888

Text #1

Max Range: 3.2287. Min Range: -3.2287

Max Act: 3.0989. Min Act: -0.0000

Data Index: 1054653 (The Pile)

Max Activating Token Index: 155

Text #2

Max Range: 3.2287. Min Range: -3.2287

Max Act: 3.2237. Min Act: 0.0000

Data Index: 1851755 (The Pile)

Max Activating Token Index: 817

Text #3

Max Range: 3.2287. Min Range: -3.2287

Max Act: 3.2287. Min Act: -0.0000

Data Index: 160023 (The Pile)

Max Activating Token Index: 154

Text #4

Max Range: 3.2287. Min Range: -3.2287

Max Act: 3.0684. Min Act: -0.0000

Data Index: 178905 (The Pile)

Max Activating Token Index: 48

Text #5

Max Range: 3.2287. Min Range: -3.2287

Max Act: 2.9286. Min Act: -0.0000

Data Index: 662571 (The Pile)

Max Activating Token Index: 622

Text #6

Max Range: 3.2287. Min Range: -3.2287

Max Act: 3.0939. Min Act: -0.0000

Data Index: 915130 (The Pile)

Max Activating Token Index: 217

Text #7

Max Range: 3.2287. Min Range: -3.2287

Max Act: 2.9052. Min Act: -0.0000

Data Index: 1138425 (The Pile)

Max Activating Token Index: 230

Text #8

Max Range: 3.2287. Min Range: -3.2287

Max Act: 2.9320. Min Act: -0.0000

Data Index: 996851 (The Pile)

Max Activating Token Index: 57

Text #9

Max Range: 3.2287. Min Range: -3.2287

Max Act: 2.7687. Min Act: -0.0000

Data Index: 295487 (The Pile)

Max Activating Token Index: 447

Text #10

Max Range: 3.2287. Min Range: -3.2287

Max Act: 2.8595. Min Act: -0.0000

Data Index: 21127 (The Pile)

Max Activating Token Index: 751

Text #11

Max Range: 3.2287. Min Range: -3.2287

Max Act: 2.8594. Min Act: -0.0000

Data Index: 597749 (The Pile)

Max Activating Token Index: 385

Text #12

Max Range: 3.2287. Min Range: -3.2287

Max Act: 2.7102. Min Act: -0.0000

Data Index: 623617 (The Pile)

Max Activating Token Index: 184

Text #13

Max Range: 3.2287. Min Range: -3.2287

Max Act: 2.8217. Min Act: -0.0000

Data Index: 1483255 (The Pile)

Max Activating Token Index: 1022

Text #14

Max Range: 3.2287. Min Range: -3.2287

Max Act: 2.7031. Min Act: -0.0000

Data Index: 1656532 (The Pile)

Max Activating Token Index: 152

Text #15

Max Range: 3.2287. Min Range: -3.2287

Max Act: 2.7213. Min Act: 0.0000

Data Index: 1817503 (The Pile)

Max Activating Token Index: 569

Text #16

Max Range: 3.2287. Min Range: -3.2287

Max Act: 2.6730. Min Act: -0.0000

Data Index: 776940 (The Pile)

Max Activating Token Index: 182

Text #17

Max Range: 3.2287. Min Range: -3.2287

Max Act: 2.8163. Min Act: -0.0000

Data Index: 43080 (The Pile)

Max Activating Token Index: 440

Text #18

Max Range: 3.2287. Min Range: -3.2287

Max Act: 2.5932. Min Act: -0.0000

Data Index: 1044117 (The Pile)

Max Activating Token Index: 253

Text #19

Max Range: 3.2287. Min Range: -3.2287

Max Act: 2.8954. Min Act: -0.0000

Data Index: 1180665 (The Pile)

Max Activating Token Index: 855