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

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

Neuron 243 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3151. Min Range: -1.3151

Max Act: 1.3151. Min Act: -0.0000

Data Index: 430831 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 1.3151. Min Range: -1.3151

Max Act: 1.2129. Min Act: -0.0000

Data Index: 572199 (C4 (Web Text))

Max Activating Token Index: 887

Text #2

Max Range: 1.3151. Min Range: -1.3151

Max Act: 1.0394. Min Act: -0.0000

Data Index: 18405 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 1.3151. Min Range: -1.3151

Max Act: 1.0122. Min Act: -0.0000

Data Index: 898099 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 1.3151. Min Range: -1.3151

Max Act: 1.0006. Min Act: -0.0000

Data Index: 210771 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 1.3151. Min Range: -1.3151

Max Act: 0.9436. Min Act: -0.0000

Data Index: 228702 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 1.3151. Min Range: -1.3151

Max Act: 0.9248. Min Act: -0.0000

Data Index: 1055915 (C4 (Web Text))

Max Activating Token Index: 387

Text #7

Max Range: 1.3151. Min Range: -1.3151

Max Act: 0.8550. Min Act: -0.0000

Data Index: 749604 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 1.3151. Min Range: -1.3151

Max Act: 0.8801. Min Act: -0.0000

Data Index: 382761 (C4 (Web Text))

Max Activating Token Index: 688

Text #9

Max Range: 1.3151. Min Range: -1.3151

Max Act: 0.7885. Min Act: -0.0000

Data Index: 909000 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 1.3151. Min Range: -1.3151

Max Act: 0.8596. Min Act: -0.0000

Data Index: 1121109 (C4 (Web Text))

Max Activating Token Index: 989

Text #11

Max Range: 1.3151. Min Range: -1.3151

Max Act: 0.9296. Min Act: -0.0000

Data Index: 1061005 (C4 (Web Text))

Max Activating Token Index: 971

Text #12

Max Range: 1.3151. Min Range: -1.3151

Max Act: 0.9071. Min Act: -0.0000

Data Index: 924451 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 1.3151. Min Range: -1.3151

Max Act: 0.8824. Min Act: -0.0000

Data Index: 1045513 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 1.3151. Min Range: -1.3151

Max Act: 0.8577. Min Act: -0.0001

Data Index: 45831 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 1.3151. Min Range: -1.3151

Max Act: 0.8440. Min Act: -0.0000

Data Index: 39201 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 1.3151. Min Range: -1.3151

Max Act: 0.8013. Min Act: -0.0000

Data Index: 1246971 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 1.3151. Min Range: -1.3151

Max Act: 0.7874. Min Act: -0.0000

Data Index: 72031 (C4 (Web Text))

Max Activating Token Index: 290

Text #18

Max Range: 1.3151. Min Range: -1.3151

Max Act: 0.7884. Min Act: -0.0000

Data Index: 877478 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 1.3151. Min Range: -1.3151

Max Act: 0.7841. Min Act: -0.0000

Data Index: 48823 (C4 (Web Text))

Max Activating Token Index: 790