Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 628 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4463. Min Range: -1.4463

Max Act: 1.2486. Min Act: -0.0001

Data Index: 171284 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 1.4463. Min Range: -1.4463

Max Act: 1.4463. Min Act: -0.0001

Data Index: 781032 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 1.4463. Min Range: -1.4463

Max Act: 1.0086. Min Act: -0.0001

Data Index: 759200 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 1.4463. Min Range: -1.4463

Max Act: 1.2006. Min Act: -0.0001

Data Index: 1024887 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 1.4463. Min Range: -1.4463

Max Act: 1.0704. Min Act: -0.0001

Data Index: 445298 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 1.4463. Min Range: -1.4463

Max Act: 1.0974. Min Act: -0.0001

Data Index: 366783 (C4 (Web Text))

Max Activating Token Index: 564

Text #6

Max Range: 1.4463. Min Range: -1.4463

Max Act: 0.8200. Min Act: -0.0001

Data Index: 506837 (C4 (Web Text))

Max Activating Token Index: 358

Text #7

Max Range: 1.4463. Min Range: -1.4463

Max Act: 0.9842. Min Act: -0.0001

Data Index: 547891 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 1.4463. Min Range: -1.4463

Max Act: 1.0500. Min Act: -0.0001

Data Index: 136484 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 1.4463. Min Range: -1.4463

Max Act: 0.9813. Min Act: -0.0001

Data Index: 539733 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 1.4463. Min Range: -1.4463

Max Act: 0.9046. Min Act: -0.0001

Data Index: 174597 (C4 (Web Text))

Max Activating Token Index: 814

Text #11

Max Range: 1.4463. Min Range: -1.4463

Max Act: 0.9139. Min Act: -0.0001

Data Index: 763940 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 1.4463. Min Range: -1.4463

Max Act: 0.8448. Min Act: -0.0001

Data Index: 291288 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 1.4463. Min Range: -1.4463

Max Act: 0.9618. Min Act: -0.0001

Data Index: 904999 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 1.4463. Min Range: -1.4463

Max Act: 1.0009. Min Act: -0.0001

Data Index: 950438 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 1.4463. Min Range: -1.4463

Max Act: 0.8641. Min Act: -0.0001

Data Index: 61584 (C4 (Web Text))

Max Activating Token Index: 717

Text #16

Max Range: 1.4463. Min Range: -1.4463

Max Act: 0.8794. Min Act: -0.0001

Data Index: 1260762 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 1.4463. Min Range: -1.4463

Max Act: 0.9302. Min Act: -0.0001

Data Index: 175890 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 1.4463. Min Range: -1.4463

Max Act: 0.9283. Min Act: -0.0001

Data Index: 353569 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 1.4463. Min Range: -1.4463

Max Act: 0.8999. Min Act: -0.0001

Data Index: 1047651 (C4 (Web Text))

Max Activating Token Index: 824