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

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

Neuron 2595 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.2069. Min Act: -0.0000

Data Index: 427389 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.1521. Min Act: -0.0000

Data Index: 493736 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.2410. Min Act: -0.0001

Data Index: 1112546 (C4 (Web Text))

Max Activating Token Index: 899

Text #3

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.1830. Min Act: -0.0001

Data Index: 1172304 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.1423. Min Act: -0.0001

Data Index: 312522 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.1013. Min Act: -0.0001

Data Index: 758902 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.1423. Min Act: -0.0001

Data Index: 19879 (C4 (Web Text))

Max Activating Token Index: 590

Text #7

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.1336. Min Act: -0.0001

Data Index: 499045 (C4 (Web Text))

Max Activating Token Index: 794

Text #8

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.0997. Min Act: -0.0001

Data Index: 125759 (C4 (Web Text))

Max Activating Token Index: 91

Text #9

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.1284. Min Act: -0.0001

Data Index: 34533 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.1090. Min Act: -0.0001

Data Index: 688803 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.0745. Min Act: -0.0001

Data Index: 321094 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.0807. Min Act: -0.0001

Data Index: 702526 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.0869. Min Act: -0.0001

Data Index: 375835 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.0901. Min Act: -0.0001

Data Index: 36452 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.0793. Min Act: -0.0001

Data Index: 454975 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.0815. Min Act: -0.0001

Data Index: 567057 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.0633. Min Act: -0.0001

Data Index: 1289258 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.0775. Min Act: -0.0001

Data Index: 463034 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.0927. Min Act: -0.0001

Data Index: 639409 (C4 (Web Text))

Max Activating Token Index: 663