Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 466 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5789. Min Act: -0.0001

Data Index: 870646 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5508. Min Act: -0.0002

Data Index: 19533 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5429. Min Act: -0.0002

Data Index: 637084 (C4 (Web Text))

Max Activating Token Index: 442

Text #3

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5343. Min Act: -0.0002

Data Index: 301497 (C4 (Web Text))

Max Activating Token Index: 972

Text #4

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5079. Min Act: -0.0002

Data Index: 137978 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5430. Min Act: -0.0001

Data Index: 486675 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4923. Min Act: -0.0001

Data Index: 298747 (C4 (Web Text))

Max Activating Token Index: 871

Text #7

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4991. Min Act: -0.0002

Data Index: 32602 (C4 (Web Text))

Max Activating Token Index: 605

Text #8

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5195. Min Act: -0.0001

Data Index: 753681 (C4 (Web Text))

Max Activating Token Index: 708

Text #9

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5021. Min Act: -0.0001

Data Index: 127075 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5288. Min Act: -0.0002

Data Index: 999207 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4975. Min Act: -0.0002

Data Index: 941305 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5372. Min Act: -0.0002

Data Index: 11103 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4768. Min Act: -0.0002

Data Index: 1174971 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4967. Min Act: -0.0001

Data Index: 610411 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4790. Min Act: -0.0002

Data Index: 177131 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4950. Min Act: -0.0002

Data Index: 1140836 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4901. Min Act: -0.0002

Data Index: 733331 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4903. Min Act: -0.0001

Data Index: 28889 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4724. Min Act: -0.0002

Data Index: 1003576 (C4 (Web Text))

Max Activating Token Index: 699