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

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

Neuron 4918 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1726. Min Range: -2.1726

Max Act: 2.1726. Min Act: -0.0000

Data Index: 156629 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 2.1726. Min Range: -2.1726

Max Act: 2.0248. Min Act: -0.0000

Data Index: 920737 (C4 (Web Text))

Max Activating Token Index: 982

Text #2

Max Range: 2.1726. Min Range: -2.1726

Max Act: 2.1129. Min Act: -0.0000

Data Index: 1006764 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 2.1726. Min Range: -2.1726

Max Act: 1.6530. Min Act: -0.0000

Data Index: 723610 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 2.1726. Min Range: -2.1726

Max Act: 1.8327. Min Act: -0.0000

Data Index: 441214 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 2.1726. Min Range: -2.1726

Max Act: 1.6885. Min Act: -0.0000

Data Index: 20817 (C4 (Web Text))

Max Activating Token Index: 417

Text #6

Max Range: 2.1726. Min Range: -2.1726

Max Act: 1.5044. Min Act: -0.0000

Data Index: 539919 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 2.1726. Min Range: -2.1726

Max Act: 1.6734. Min Act: -0.0000

Data Index: 156060 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 2.1726. Min Range: -2.1726

Max Act: 1.6255. Min Act: -0.0000

Data Index: 1001320 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 2.1726. Min Range: -2.1726

Max Act: 1.5350. Min Act: -0.0000

Data Index: 258609 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 2.1726. Min Range: -2.1726

Max Act: 1.5353. Min Act: -0.0000

Data Index: 1281238 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 2.1726. Min Range: -2.1726

Max Act: 1.5257. Min Act: -0.0000

Data Index: 78494 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 2.1726. Min Range: -2.1726

Max Act: 1.5135. Min Act: -0.0000

Data Index: 1075876 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 2.1726. Min Range: -2.1726

Max Act: 1.5115. Min Act: -0.0000

Data Index: 628910 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 2.1726. Min Range: -2.1726

Max Act: 1.5128. Min Act: -0.0000

Data Index: 447389 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 2.1726. Min Range: -2.1726

Max Act: 1.5940. Min Act: -0.0000

Data Index: 304077 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 2.1726. Min Range: -2.1726

Max Act: 1.4906. Min Act: -0.0000

Data Index: 515869 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 2.1726. Min Range: -2.1726

Max Act: 1.5773. Min Act: -0.0000

Data Index: 1128302 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 2.1726. Min Range: -2.1726

Max Act: 1.4771. Min Act: -0.0000

Data Index: 297789 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 2.1726. Min Range: -2.1726

Max Act: 1.4013. Min Act: -0.0000

Data Index: 1132226 (C4 (Web Text))

Max Activating Token Index: 1006