Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3546 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5884. Min Range: -0.5884

Max Act: 0.5753. Min Act: -0.0001

Data Index: 669625 (C4 (Web Text))

Max Activating Token Index: 554

Text #1

Max Range: 0.5884. Min Range: -0.5884

Max Act: 0.5777. Min Act: -0.0001

Data Index: 411562 (C4 (Web Text))

Max Activating Token Index: 495

Text #2

Max Range: 0.5884. Min Range: -0.5884

Max Act: 0.5884. Min Act: -0.0000

Data Index: 222692 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 0.5884. Min Range: -0.5884

Max Act: 0.5383. Min Act: -0.0000

Data Index: 663714 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 0.5884. Min Range: -0.5884

Max Act: 0.5308. Min Act: -0.0001

Data Index: 803653 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 0.5884. Min Range: -0.5884

Max Act: 0.5420. Min Act: -0.0001

Data Index: 373494 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 0.5884. Min Range: -0.5884

Max Act: 0.5258. Min Act: -0.0001

Data Index: 95071 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 0.5884. Min Range: -0.5884

Max Act: 0.5375. Min Act: -0.0001

Data Index: 306701 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 0.5884. Min Range: -0.5884

Max Act: 0.5396. Min Act: -0.0000

Data Index: 17087 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 0.5884. Min Range: -0.5884

Max Act: 0.5178. Min Act: -0.0001

Data Index: 138263 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 0.5884. Min Range: -0.5884

Max Act: 0.5466. Min Act: -0.0001

Data Index: 235529 (C4 (Web Text))

Max Activating Token Index: 538

Text #11

Max Range: 0.5884. Min Range: -0.5884

Max Act: 0.5246. Min Act: -0.0000

Data Index: 640787 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 0.5884. Min Range: -0.5884

Max Act: 0.5085. Min Act: -0.0001

Data Index: 805917 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 0.5884. Min Range: -0.5884

Max Act: 0.5031. Min Act: -0.0001

Data Index: 229439 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 0.5884. Min Range: -0.5884

Max Act: 0.5176. Min Act: -0.0001

Data Index: 391169 (C4 (Web Text))

Max Activating Token Index: 925

Text #15

Max Range: 0.5884. Min Range: -0.5884

Max Act: 0.4974. Min Act: -0.0001

Data Index: 605574 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 0.5884. Min Range: -0.5884

Max Act: 0.4986. Min Act: -0.0001

Data Index: 1088955 (C4 (Web Text))

Max Activating Token Index: 684

Text #17

Max Range: 0.5884. Min Range: -0.5884

Max Act: 0.5154. Min Act: -0.0001

Data Index: 368384 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 0.5884. Min Range: -0.5884

Max Act: 0.5109. Min Act: -0.0001

Data Index: 1050350 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 0.5884. Min Range: -0.5884

Max Act: 0.5102. Min Act: -0.0001

Data Index: 233030 (C4 (Web Text))

Max Activating Token Index: 603