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

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

Neuron 1718 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: 4.1638. Min Range: -4.1638

Max Act: 4.1638. Min Act: -0.0000

Data Index: 1279111 (C4 (Web Text))

Max Activating Token Index: 524

Text #1

Max Range: 4.1638. Min Range: -4.1638

Max Act: 3.7692. Min Act: -0.0000

Data Index: 1034838 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 4.1638. Min Range: -4.1638

Max Act: 3.8807. Min Act: -0.0000

Data Index: 386699 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 4.1638. Min Range: -4.1638

Max Act: 3.1696. Min Act: -0.0000

Data Index: 1140352 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 4.1638. Min Range: -4.1638

Max Act: 3.3187. Min Act: -0.0000

Data Index: 982998 (C4 (Web Text))

Max Activating Token Index: 584

Text #5

Max Range: 4.1638. Min Range: -4.1638

Max Act: 2.8536. Min Act: -0.0000

Data Index: 192721 (C4 (Web Text))

Max Activating Token Index: 921

Text #6

Max Range: 4.1638. Min Range: -4.1638

Max Act: 3.1266. Min Act: -0.0000

Data Index: 878144 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 4.1638. Min Range: -4.1638

Max Act: 2.9934. Min Act: -0.0000

Data Index: 655512 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 4.1638. Min Range: -4.1638

Max Act: 3.0619. Min Act: -0.0000

Data Index: 1349709 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 4.1638. Min Range: -4.1638

Max Act: 3.0150. Min Act: -0.0000

Data Index: 565311 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 4.1638. Min Range: -4.1638

Max Act: 2.8841. Min Act: -0.0000

Data Index: 367001 (C4 (Web Text))

Max Activating Token Index: 279

Text #11

Max Range: 4.1638. Min Range: -4.1638

Max Act: 2.7088. Min Act: -0.0000

Data Index: 611733 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 4.1638. Min Range: -4.1638

Max Act: 2.9918. Min Act: -0.0000

Data Index: 1307698 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 4.1638. Min Range: -4.1638

Max Act: 3.1150. Min Act: -0.0000

Data Index: 635489 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 4.1638. Min Range: -4.1638

Max Act: 2.9874. Min Act: -0.0000

Data Index: 175413 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 4.1638. Min Range: -4.1638

Max Act: 2.9874. Min Act: -0.0000

Data Index: 1173882 (C4 (Web Text))

Max Activating Token Index: 290

Text #16

Max Range: 4.1638. Min Range: -4.1638

Max Act: 2.8218. Min Act: -0.0000

Data Index: 959029 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 4.1638. Min Range: -4.1638

Max Act: 2.6358. Min Act: -0.0000

Data Index: 69140 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 4.1638. Min Range: -4.1638

Max Act: 2.7463. Min Act: -0.0000

Data Index: 377085 (C4 (Web Text))

Max Activating Token Index: 343

Text #19

Max Range: 4.1638. Min Range: -4.1638

Max Act: 3.0427. Min Act: -0.0000

Data Index: 864490 (C4 (Web Text))

Max Activating Token Index: 607