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

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

Neuron 2528 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: 5.1790. Min Range: -5.1790

Max Act: 5.0368. Min Act: -0.0001

Data Index: 944496 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 5.1790. Min Range: -5.1790

Max Act: 4.8447. Min Act: -0.0001

Data Index: 520223 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 5.1790. Min Range: -5.1790

Max Act: 5.1790. Min Act: -0.0001

Data Index: 402572 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 5.1790. Min Range: -5.1790

Max Act: 5.0455. Min Act: -0.0001

Data Index: 962988 (C4 (Web Text))

Max Activating Token Index: 585

Text #4

Max Range: 5.1790. Min Range: -5.1790

Max Act: 4.7254. Min Act: -0.0001

Data Index: 813797 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 5.1790. Min Range: -5.1790

Max Act: 5.0129. Min Act: -0.0001

Data Index: 1200527 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 5.1790. Min Range: -5.1790

Max Act: 4.4732. Min Act: -0.0001

Data Index: 1282986 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 5.1790. Min Range: -5.1790

Max Act: 4.2931. Min Act: -0.0001

Data Index: 1158684 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 5.1790. Min Range: -5.1790

Max Act: 4.6066. Min Act: -0.0001

Data Index: 471881 (C4 (Web Text))

Max Activating Token Index: 655

Text #9

Max Range: 5.1790. Min Range: -5.1790

Max Act: 4.3992. Min Act: -0.0001

Data Index: 59964 (C4 (Web Text))

Max Activating Token Index: 190

Text #10

Max Range: 5.1790. Min Range: -5.1790

Max Act: 3.9506. Min Act: -0.0001

Data Index: 220255 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 5.1790. Min Range: -5.1790

Max Act: 3.6838. Min Act: -0.0001

Data Index: 722361 (C4 (Web Text))

Max Activating Token Index: 955

Text #12

Max Range: 5.1790. Min Range: -5.1790

Max Act: 4.0611. Min Act: -0.0001

Data Index: 1067074 (C4 (Web Text))

Max Activating Token Index: 954

Text #13

Max Range: 5.1790. Min Range: -5.1790

Max Act: 3.8724. Min Act: -0.0001

Data Index: 161408 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 5.1790. Min Range: -5.1790

Max Act: 4.0405. Min Act: -0.0001

Data Index: 133380 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 5.1790. Min Range: -5.1790

Max Act: 3.6614. Min Act: -0.0000

Data Index: 597 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 5.1790. Min Range: -5.1790

Max Act: 3.8054. Min Act: -0.0001

Data Index: 165889 (C4 (Web Text))

Max Activating Token Index: 891

Text #17

Max Range: 5.1790. Min Range: -5.1790

Max Act: 3.4431. Min Act: -0.0001

Data Index: 958690 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 5.1790. Min Range: -5.1790

Max Act: 3.8923. Min Act: -0.0001

Data Index: 337788 (C4 (Web Text))

Max Activating Token Index: 997

Text #19

Max Range: 5.1790. Min Range: -5.1790

Max Act: 3.5772. Min Act: -0.0000

Data Index: 738591 (C4 (Web Text))

Max Activating Token Index: 668