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

Dataset: The Pile

Neuron 2552 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.8691. Min Act: -0.0000

Data Index: 867497 (The Pile)

Max Activating Token Index: 128

Text #1

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.7380. Min Act: -0.0000

Data Index: 1112734 (The Pile)

Max Activating Token Index: 325

Text #2

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.4400. Min Act: -0.0000

Data Index: 519415 (The Pile)

Max Activating Token Index: 597

Text #3

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.5722. Min Act: -0.0000

Data Index: 1144668 (The Pile)

Max Activating Token Index: 1006

Text #4

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.4290. Min Act: -0.0000

Data Index: 406635 (The Pile)

Max Activating Token Index: 477

Text #5

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.5959. Min Act: -0.0000

Data Index: 1023652 (The Pile)

Max Activating Token Index: 905

Text #6

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.5549. Min Act: -0.0000

Data Index: 1674499 (The Pile)

Max Activating Token Index: 414

Text #7

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.5417. Min Act: -0.0000

Data Index: 1055991 (The Pile)

Max Activating Token Index: 62

Text #8

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.6381. Min Act: -0.0000

Data Index: 276306 (The Pile)

Max Activating Token Index: 152

Text #9

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.6685. Min Act: -0.0000

Data Index: 1195372 (The Pile)

Max Activating Token Index: 181

Text #10

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.4558. Min Act: -0.0000

Data Index: 1459003 (The Pile)

Max Activating Token Index: 485

Text #11

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.5301. Min Act: -0.0000

Data Index: 1931261 (The Pile)

Max Activating Token Index: 114

Text #12

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.4518. Min Act: -0.0000

Data Index: 1030634 (The Pile)

Max Activating Token Index: 609

Text #13

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.3866. Min Act: -0.0000

Data Index: 843598 (The Pile)

Max Activating Token Index: 349

Text #14

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.4657. Min Act: -0.0000

Data Index: 1358857 (The Pile)

Max Activating Token Index: 372

Text #15

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.3622. Min Act: -0.0000

Data Index: 1343382 (The Pile)

Max Activating Token Index: 685

Text #16

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.3128. Min Act: -0.0000

Data Index: 1407282 (The Pile)

Max Activating Token Index: 997

Text #17

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.3083. Min Act: -0.0000

Data Index: 687943 (The Pile)

Max Activating Token Index: 306

Text #18

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.2806. Min Act: -0.0000

Data Index: 88072 (The Pile)

Max Activating Token Index: 872

Text #19

Max Range: 1.8691. Min Range: -1.8691

Max Act: 1.4344. Min Act: -0.0000

Data Index: 200479 (The Pile)

Max Activating Token Index: 806