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

Dataset: The Pile

Neuron 1130 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: 0.8143. Min Range: -0.8143

Max Act: 0.8143. Min Act: -0.0000

Data Index: 12757 (The Pile)

Max Activating Token Index: 563

Text #1

Max Range: 0.8143. Min Range: -0.8143

Max Act: 0.7288. Min Act: -0.0000

Data Index: 933308 (The Pile)

Max Activating Token Index: 640

Text #2

Max Range: 0.8143. Min Range: -0.8143

Max Act: 0.7037. Min Act: -0.0000

Data Index: 1319209 (The Pile)

Max Activating Token Index: 371

Text #3

Max Range: 0.8143. Min Range: -0.8143

Max Act: 0.7134. Min Act: -0.0000

Data Index: 1010795 (The Pile)

Max Activating Token Index: 488

Text #4

Max Range: 0.8143. Min Range: -0.8143

Max Act: 0.6239. Min Act: -0.0000

Data Index: 752218 (The Pile)

Max Activating Token Index: 917

Text #5

Max Range: 0.8143. Min Range: -0.8143

Max Act: 0.6430. Min Act: -0.0000

Data Index: 1041734 (The Pile)

Max Activating Token Index: 433

Text #6

Max Range: 0.8143. Min Range: -0.8143

Max Act: 0.5795. Min Act: -0.0000

Data Index: 1419652 (The Pile)

Max Activating Token Index: 297

Text #7

Max Range: 0.8143. Min Range: -0.8143

Max Act: 0.6171. Min Act: -0.0000

Data Index: 1206623 (The Pile)

Max Activating Token Index: 179

Text #8

Max Range: 0.8143. Min Range: -0.8143

Max Act: 0.6196. Min Act: -0.0000

Data Index: 706593 (The Pile)

Max Activating Token Index: 550

Text #9

Max Range: 0.8143. Min Range: -0.8143

Max Act: 0.7053. Min Act: -0.0000

Data Index: 513055 (The Pile)

Max Activating Token Index: 232

Text #10

Max Range: 0.8143. Min Range: -0.8143

Max Act: 0.5596. Min Act: -0.0000

Data Index: 673749 (The Pile)

Max Activating Token Index: 362

Text #11

Max Range: 0.8143. Min Range: -0.8143

Max Act: 0.5131. Min Act: -0.0000

Data Index: 1426572 (The Pile)

Max Activating Token Index: 882

Text #12

Max Range: 0.8143. Min Range: -0.8143

Max Act: 0.5658. Min Act: -0.0000

Data Index: 616424 (The Pile)

Max Activating Token Index: 896

Text #13

Max Range: 0.8143. Min Range: -0.8143

Max Act: 0.5428. Min Act: -0.0000

Data Index: 1072033 (The Pile)

Max Activating Token Index: 427

Text #14

Max Range: 0.8143. Min Range: -0.8143

Max Act: 0.5438. Min Act: -0.0000

Data Index: 1053359 (The Pile)

Max Activating Token Index: 81

Text #15

Max Range: 0.8143. Min Range: -0.8143

Max Act: 0.5278. Min Act: -0.0000

Data Index: 1876340 (The Pile)

Max Activating Token Index: 655

Text #16

Max Range: 0.8143. Min Range: -0.8143

Max Act: 0.5222. Min Act: -0.0000

Data Index: 1526505 (The Pile)

Max Activating Token Index: 1008

Text #17

Max Range: 0.8143. Min Range: -0.8143

Max Act: 0.5429. Min Act: -0.0000

Data Index: 968734 (The Pile)

Max Activating Token Index: 365

Text #18

Max Range: 0.8143. Min Range: -0.8143

Max Act: 0.5019. Min Act: -0.0000

Data Index: 1839975 (The Pile)

Max Activating Token Index: 439

Text #19

Max Range: 0.8143. Min Range: -0.8143

Max Act: 0.5770. Min Act: -0.0000

Data Index: 570994 (The Pile)

Max Activating Token Index: 557