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

Dataset: The Pile

Neuron 4513 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7417. Min Range: -1.7417

Max Act: 1.6428. Min Act: -0.0000

Data Index: 427854 (The Pile)

Max Activating Token Index: 234

Text #1

Max Range: 1.7417. Min Range: -1.7417

Max Act: 1.7305. Min Act: -0.0000

Data Index: 1256430 (The Pile)

Max Activating Token Index: 833

Text #2

Max Range: 1.7417. Min Range: -1.7417

Max Act: 1.7093. Min Act: -0.0000

Data Index: 1341689 (The Pile)

Max Activating Token Index: 185

Text #3

Max Range: 1.7417. Min Range: -1.7417

Max Act: 1.6663. Min Act: -0.0000

Data Index: 1120781 (The Pile)

Max Activating Token Index: 359

Text #4

Max Range: 1.7417. Min Range: -1.7417

Max Act: 1.7417. Min Act: -0.0000

Data Index: 1186329 (The Pile)

Max Activating Token Index: 482

Text #5

Max Range: 1.7417. Min Range: -1.7417

Max Act: 1.4396. Min Act: -0.0000

Data Index: 210155 (The Pile)

Max Activating Token Index: 789

Text #6

Max Range: 1.7417. Min Range: -1.7417

Max Act: 1.6431. Min Act: -0.0000

Data Index: 16755 (The Pile)

Max Activating Token Index: 109

Text #7

Max Range: 1.7417. Min Range: -1.7417

Max Act: 1.6458. Min Act: -0.0000

Data Index: 851539 (The Pile)

Max Activating Token Index: 188

Text #8

Max Range: 1.7417. Min Range: -1.7417

Max Act: 1.6292. Min Act: -0.0000

Data Index: 637080 (The Pile)

Max Activating Token Index: 52

Text #9

Max Range: 1.7417. Min Range: -1.7417

Max Act: 1.5438. Min Act: -0.0000

Data Index: 1830221 (The Pile)

Max Activating Token Index: 445

Text #10

Max Range: 1.7417. Min Range: -1.7417

Max Act: 1.3482. Min Act: -0.0000

Data Index: 1853946 (The Pile)

Max Activating Token Index: 479

Text #11

Max Range: 1.7417. Min Range: -1.7417

Max Act: 1.6936. Min Act: -0.0000

Data Index: 726439 (The Pile)

Max Activating Token Index: 77

Text #12

Max Range: 1.7417. Min Range: -1.7417

Max Act: 1.7034. Min Act: -0.0000

Data Index: 421396 (The Pile)

Max Activating Token Index: 100

Text #13

Max Range: 1.7417. Min Range: -1.7417

Max Act: 1.5087. Min Act: -0.0000

Data Index: 112028 (The Pile)

Max Activating Token Index: 168

Text #14

Max Range: 1.7417. Min Range: -1.7417

Max Act: 1.5789. Min Act: -0.0000

Data Index: 1092783 (The Pile)

Max Activating Token Index: 321

Text #15

Max Range: 1.7417. Min Range: -1.7417

Max Act: 1.5629. Min Act: -0.0000

Data Index: 979382 (The Pile)

Max Activating Token Index: 219

Text #16

Max Range: 1.7417. Min Range: -1.7417

Max Act: 1.5687. Min Act: -0.0000

Data Index: 963505 (The Pile)

Max Activating Token Index: 977

Text #17

Max Range: 1.7417. Min Range: -1.7417

Max Act: 1.6471. Min Act: -0.0000

Data Index: 1599798 (The Pile)

Max Activating Token Index: 885

Text #18

Max Range: 1.7417. Min Range: -1.7417

Max Act: 1.5647. Min Act: -0.0000

Data Index: 44918 (The Pile)

Max Activating Token Index: 294

Text #19

Max Range: 1.7417. Min Range: -1.7417

Max Act: 1.5022. Min Act: -0.0000

Data Index: 331231 (The Pile)

Max Activating Token Index: 269