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

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

Neuron 2245 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.3696. Min Act: -0.0000

Data Index: 989211 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.2050. Min Act: -0.0000

Data Index: 532030 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.2057. Min Act: -0.0000

Data Index: 210483 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.1923. Min Act: -0.0000

Data Index: 690440 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.1921. Min Act: -0.0001

Data Index: 448258 (C4 (Web Text))

Max Activating Token Index: 387

Text #5

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.1973. Min Act: -0.0000

Data Index: 1202652 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.1795. Min Act: -0.0000

Data Index: 308867 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.1789. Min Act: -0.0000

Data Index: 1358752 (C4 (Web Text))

Max Activating Token Index: 276

Text #8

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.1788. Min Act: -0.0000

Data Index: 844096 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.1844. Min Act: -0.0000

Data Index: 736776 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.1747. Min Act: -0.0000

Data Index: 625325 (C4 (Web Text))

Max Activating Token Index: 781

Text #11

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.1587. Min Act: -0.0001

Data Index: 437144 (C4 (Web Text))

Max Activating Token Index: 803

Text #12

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.1788. Min Act: -0.0001

Data Index: 1288261 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.1648. Min Act: -0.0001

Data Index: 515480 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.1579. Min Act: -0.0000

Data Index: 826311 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.1697. Min Act: -0.0000

Data Index: 780334 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.1445. Min Act: -0.0001

Data Index: 258527 (C4 (Web Text))

Max Activating Token Index: 216

Text #17

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.1552. Min Act: -0.0000

Data Index: 898009 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.1583. Min Act: -0.0001

Data Index: 1325484 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 0.3696. Min Range: -0.3696

Max Act: 0.1533. Min Act: -0.0000

Data Index: 348497 (C4 (Web Text))

Max Activating Token Index: 553