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

Dataset: The Pile

Neuron 4374 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: 1.3633. Min Range: -1.3633

Max Act: 1.3423. Min Act: -0.0000

Data Index: 1854621 (The Pile)

Max Activating Token Index: 244

Text #1

Max Range: 1.3633. Min Range: -1.3633

Max Act: 1.3633. Min Act: -0.0000

Data Index: 727075 (The Pile)

Max Activating Token Index: 844

Text #2

Max Range: 1.3633. Min Range: -1.3633

Max Act: 1.2376. Min Act: 0.0000

Data Index: 1325255 (The Pile)

Max Activating Token Index: 261

Text #3

Max Range: 1.3633. Min Range: -1.3633

Max Act: 1.1266. Min Act: -0.0000

Data Index: 685321 (The Pile)

Max Activating Token Index: 140

Text #4

Max Range: 1.3633. Min Range: -1.3633

Max Act: 1.0956. Min Act: -0.0000

Data Index: 553399 (The Pile)

Max Activating Token Index: 56

Text #5

Max Range: 1.3633. Min Range: -1.3633

Max Act: 0.9995. Min Act: -0.0000

Data Index: 771176 (The Pile)

Max Activating Token Index: 654

Text #6

Max Range: 1.3633. Min Range: -1.3633

Max Act: 0.9411. Min Act: -0.0000

Data Index: 1264180 (The Pile)

Max Activating Token Index: 300

Text #7

Max Range: 1.3633. Min Range: -1.3633

Max Act: 0.7792. Min Act: -0.0000

Data Index: 1393493 (The Pile)

Max Activating Token Index: 178

Text #8

Max Range: 1.3633. Min Range: -1.3633

Max Act: 0.8046. Min Act: -0.0000

Data Index: 1057029 (The Pile)

Max Activating Token Index: 325

Text #9

Max Range: 1.3633. Min Range: -1.3633

Max Act: 0.8018. Min Act: -0.0000

Data Index: 47395 (The Pile)

Max Activating Token Index: 471

Text #10

Max Range: 1.3633. Min Range: -1.3633

Max Act: 0.7503. Min Act: 0.0000

Data Index: 14117 (The Pile)

Max Activating Token Index: 287

Text #11

Max Range: 1.3633. Min Range: -1.3633

Max Act: 0.7134. Min Act: -0.0000

Data Index: 838407 (The Pile)

Max Activating Token Index: 247

Text #12

Max Range: 1.3633. Min Range: -1.3633

Max Act: 0.7745. Min Act: -0.0000

Data Index: 424525 (The Pile)

Max Activating Token Index: 607

Text #13

Max Range: 1.3633. Min Range: -1.3633

Max Act: 0.7270. Min Act: -0.0000

Data Index: 816516 (The Pile)

Max Activating Token Index: 180

Text #14

Max Range: 1.3633. Min Range: -1.3633

Max Act: 0.7082. Min Act: -0.0000

Data Index: 1037860 (The Pile)

Max Activating Token Index: 751

Text #15

Max Range: 1.3633. Min Range: -1.3633

Max Act: 0.7106. Min Act: -0.0000

Data Index: 1359043 (The Pile)

Max Activating Token Index: 752

Text #16

Max Range: 1.3633. Min Range: -1.3633

Max Act: 0.7423. Min Act: -0.0000

Data Index: 555406 (The Pile)

Max Activating Token Index: 491

Text #17

Max Range: 1.3633. Min Range: -1.3633

Max Act: 0.6760. Min Act: -0.0000

Data Index: 309277 (The Pile)

Max Activating Token Index: 642

Text #18

Max Range: 1.3633. Min Range: -1.3633

Max Act: 0.6922. Min Act: -0.0000

Data Index: 1087016 (The Pile)

Max Activating Token Index: 958

Text #19

Max Range: 1.3633. Min Range: -1.3633

Max Act: 0.6613. Min Act: -0.0000

Data Index: 610517 (The Pile)

Max Activating Token Index: 734