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

Dataset: The Pile

Neuron 1705 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: 0.8699. Min Range: -0.8699

Max Act: 0.8699. Min Act: -0.0000

Data Index: 1642968 (The Pile)

Max Activating Token Index: 15

Text #1

Max Range: 0.8699. Min Range: -0.8699

Max Act: 0.8076. Min Act: -0.0000

Data Index: 555397 (The Pile)

Max Activating Token Index: 626

Text #2

Max Range: 0.8699. Min Range: -0.8699

Max Act: 0.8333. Min Act: -0.0000

Data Index: 213192 (The Pile)

Max Activating Token Index: 182

Text #3

Max Range: 0.8699. Min Range: -0.8699

Max Act: 0.7060. Min Act: -0.0000

Data Index: 1640301 (The Pile)

Max Activating Token Index: 54

Text #4

Max Range: 0.8699. Min Range: -0.8699

Max Act: 0.7253. Min Act: -0.0000

Data Index: 1266821 (The Pile)

Max Activating Token Index: 892

Text #5

Max Range: 0.8699. Min Range: -0.8699

Max Act: 0.7034. Min Act: -0.0000

Data Index: 264231 (The Pile)

Max Activating Token Index: 56

Text #6

Max Range: 0.8699. Min Range: -0.8699

Max Act: 0.7218. Min Act: -0.0000

Data Index: 911911 (The Pile)

Max Activating Token Index: 267

Text #7

Max Range: 0.8699. Min Range: -0.8699

Max Act: 0.6651. Min Act: -0.0000

Data Index: 1431861 (The Pile)

Max Activating Token Index: 660

Text #8

Max Range: 0.8699. Min Range: -0.8699

Max Act: 0.6687. Min Act: -0.0000

Data Index: 1405009 (The Pile)

Max Activating Token Index: 637

Text #9

Max Range: 0.8699. Min Range: -0.8699

Max Act: 0.5797. Min Act: -0.0000

Data Index: 197950 (The Pile)

Max Activating Token Index: 857

Text #10

Max Range: 0.8699. Min Range: -0.8699

Max Act: 0.6662. Min Act: -0.0000

Data Index: 1747142 (The Pile)

Max Activating Token Index: 822

Text #11

Max Range: 0.8699. Min Range: -0.8699

Max Act: 0.6929. Min Act: -0.0000

Data Index: 1719935 (The Pile)

Max Activating Token Index: 450

Text #12

Max Range: 0.8699. Min Range: -0.8699

Max Act: 0.6100. Min Act: -0.0000

Data Index: 1866567 (The Pile)

Max Activating Token Index: 363

Text #13

Max Range: 0.8699. Min Range: -0.8699

Max Act: 0.6436. Min Act: -0.0000

Data Index: 474406 (The Pile)

Max Activating Token Index: 399

Text #14

Max Range: 0.8699. Min Range: -0.8699

Max Act: 0.5894. Min Act: -0.0000

Data Index: 1110497 (The Pile)

Max Activating Token Index: 91

Text #15

Max Range: 0.8699. Min Range: -0.8699

Max Act: 0.6298. Min Act: -0.0000

Data Index: 1358273 (The Pile)

Max Activating Token Index: 365

Text #16

Max Range: 0.8699. Min Range: -0.8699

Max Act: 0.6280. Min Act: -0.0000

Data Index: 1929918 (The Pile)

Max Activating Token Index: 436

Text #17

Max Range: 0.8699. Min Range: -0.8699

Max Act: 0.6285. Min Act: -0.0000

Data Index: 1077513 (The Pile)

Max Activating Token Index: 911

Text #18

Max Range: 0.8699. Min Range: -0.8699

Max Act: 0.6222. Min Act: -0.0000

Data Index: 1472270 (The Pile)

Max Activating Token Index: 109

Text #19

Max Range: 0.8699. Min Range: -0.8699

Max Act: 0.6423. Min Act: -0.0000

Data Index: 814459 (The Pile)

Max Activating Token Index: 633