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

Dataset: The Pile

Neuron 3606 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: 0.6176. Min Range: -0.6176

Max Act: 0.6056. Min Act: -0.0000

Data Index: 960501 (The Pile)

Max Activating Token Index: 281

Text #1

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.6176. Min Act: -0.0000

Data Index: 642312 (The Pile)

Max Activating Token Index: 975

Text #2

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5989. Min Act: -0.0000

Data Index: 280834 (The Pile)

Max Activating Token Index: 392

Text #3

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5550. Min Act: -0.0000

Data Index: 588933 (The Pile)

Max Activating Token Index: 792

Text #4

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5644. Min Act: -0.0000

Data Index: 1493121 (The Pile)

Max Activating Token Index: 558

Text #5

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5400. Min Act: -0.0000

Data Index: 1609481 (The Pile)

Max Activating Token Index: 693

Text #6

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5387. Min Act: -0.0000

Data Index: 275409 (The Pile)

Max Activating Token Index: 276

Text #7

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5849. Min Act: -0.0000

Data Index: 706734 (The Pile)

Max Activating Token Index: 889

Text #8

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5588. Min Act: -0.0000

Data Index: 1069656 (The Pile)

Max Activating Token Index: 469

Text #9

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5828. Min Act: -0.0000

Data Index: 870363 (The Pile)

Max Activating Token Index: 944

Text #10

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5753. Min Act: -0.0000

Data Index: 1079069 (The Pile)

Max Activating Token Index: 917

Text #11

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5166. Min Act: -0.0000

Data Index: 1286394 (The Pile)

Max Activating Token Index: 104

Text #12

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5286. Min Act: -0.0000

Data Index: 1782727 (The Pile)

Max Activating Token Index: 643

Text #13

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5562. Min Act: -0.0000

Data Index: 831241 (The Pile)

Max Activating Token Index: 736

Text #14

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.4912. Min Act: -0.0000

Data Index: 1259489 (The Pile)

Max Activating Token Index: 801

Text #15

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5307. Min Act: -0.0000

Data Index: 31318 (The Pile)

Max Activating Token Index: 435

Text #16

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5140. Min Act: -0.0000

Data Index: 732050 (The Pile)

Max Activating Token Index: 306

Text #17

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5775. Min Act: -0.0000

Data Index: 327064 (The Pile)

Max Activating Token Index: 803

Text #18

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5002. Min Act: -0.0000

Data Index: 604380 (The Pile)

Max Activating Token Index: 921

Text #19

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5037. Min Act: -0.0000

Data Index: 1731988 (The Pile)

Max Activating Token Index: 536