Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 968 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0653. Min Act: -0.0003

Data Index: 529930 (C4 (Web Text))

Max Activating Token Index: 777

Text #1

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0677. Min Act: -0.0003

Data Index: 6917 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0667. Min Act: -0.0003

Data Index: 282269 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0668. Min Act: -0.0003

Data Index: 425336 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0658. Min Act: -0.0003

Data Index: 226733 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0654. Min Act: -0.0003

Data Index: 631669 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0666. Min Act: -0.0003

Data Index: 1212035 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0631. Min Act: -0.0003

Data Index: 1013587 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0644. Min Act: -0.0003

Data Index: 889224 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0647. Min Act: -0.0003

Data Index: 9228 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0628. Min Act: -0.0003

Data Index: 256882 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0647. Min Act: -0.0004

Data Index: 1261557 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0644. Min Act: -0.0002

Data Index: 1288681 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0632. Min Act: -0.0003

Data Index: 1226945 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0636. Min Act: -0.0003

Data Index: 63486 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0615. Min Act: -0.0004

Data Index: 970107 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0630. Min Act: -0.0003

Data Index: 407334 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0621. Min Act: -0.0003

Data Index: 30069 (C4 (Web Text))

Max Activating Token Index: 672

Text #18

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0625. Min Act: -0.0003

Data Index: 729828 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 0.0677. Min Range: -0.0677

Max Act: 0.0618. Min Act: -0.0003

Data Index: 949511 (C4 (Web Text))

Max Activating Token Index: 313