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

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

Neuron 5031 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: 1.0817. Min Range: -1.0817

Max Act: 1.0817. Min Act: -0.0000

Data Index: 1308038 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 1.0817. Min Range: -1.0817

Max Act: 1.0793. Min Act: -0.0000

Data Index: 815126 (C4 (Web Text))

Max Activating Token Index: 981

Text #2

Max Range: 1.0817. Min Range: -1.0817

Max Act: 1.0704. Min Act: -0.0000

Data Index: 22317 (C4 (Web Text))

Max Activating Token Index: 653

Text #3

Max Range: 1.0817. Min Range: -1.0817

Max Act: 1.0053. Min Act: -0.0000

Data Index: 1077333 (C4 (Web Text))

Max Activating Token Index: 863

Text #4

Max Range: 1.0817. Min Range: -1.0817

Max Act: 0.9945. Min Act: -0.0000

Data Index: 431306 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 1.0817. Min Range: -1.0817

Max Act: 0.9807. Min Act: -0.0000

Data Index: 582404 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 1.0817. Min Range: -1.0817

Max Act: 0.9782. Min Act: -0.0000

Data Index: 714757 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 1.0817. Min Range: -1.0817

Max Act: 0.9114. Min Act: -0.0000

Data Index: 1018111 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 1.0817. Min Range: -1.0817

Max Act: 0.9343. Min Act: -0.0000

Data Index: 57380 (C4 (Web Text))

Max Activating Token Index: 381

Text #9

Max Range: 1.0817. Min Range: -1.0817

Max Act: 0.9215. Min Act: -0.0000

Data Index: 1301990 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 1.0817. Min Range: -1.0817

Max Act: 0.8682. Min Act: -0.0000

Data Index: 1046516 (C4 (Web Text))

Max Activating Token Index: 693

Text #11

Max Range: 1.0817. Min Range: -1.0817

Max Act: 0.9103. Min Act: -0.0000

Data Index: 258787 (C4 (Web Text))

Max Activating Token Index: 429

Text #12

Max Range: 1.0817. Min Range: -1.0817

Max Act: 0.8458. Min Act: -0.0000

Data Index: 1079045 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 1.0817. Min Range: -1.0817

Max Act: 0.8696. Min Act: -0.0000

Data Index: 501312 (C4 (Web Text))

Max Activating Token Index: 963

Text #14

Max Range: 1.0817. Min Range: -1.0817

Max Act: 0.8342. Min Act: -0.0000

Data Index: 408179 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 1.0817. Min Range: -1.0817

Max Act: 0.8841. Min Act: -0.0000

Data Index: 83355 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 1.0817. Min Range: -1.0817

Max Act: 0.7981. Min Act: -0.0000

Data Index: 30048 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 1.0817. Min Range: -1.0817

Max Act: 0.8401. Min Act: -0.0000

Data Index: 751085 (C4 (Web Text))

Max Activating Token Index: 927

Text #18

Max Range: 1.0817. Min Range: -1.0817

Max Act: 0.8680. Min Act: -0.0000

Data Index: 364740 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 1.0817. Min Range: -1.0817

Max Act: 0.8068. Min Act: -0.0000

Data Index: 807426 (C4 (Web Text))

Max Activating Token Index: 737