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

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

Neuron 960 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0950. Min Range: -1.0950

Max Act: 1.0950. Min Act: -0.0001

Data Index: 390737 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 1.0950. Min Range: -1.0950

Max Act: 0.8041. Min Act: -0.0000

Data Index: 1120585 (C4 (Web Text))

Max Activating Token Index: 440

Text #2

Max Range: 1.0950. Min Range: -1.0950

Max Act: 0.7684. Min Act: -0.0001

Data Index: 523932 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 1.0950. Min Range: -1.0950

Max Act: 0.7421. Min Act: -0.0000

Data Index: 802149 (C4 (Web Text))

Max Activating Token Index: 587

Text #4

Max Range: 1.0950. Min Range: -1.0950

Max Act: 0.6676. Min Act: -0.0000

Data Index: 1275681 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 1.0950. Min Range: -1.0950

Max Act: 0.6330. Min Act: -0.0000

Data Index: 96365 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 1.0950. Min Range: -1.0950

Max Act: 0.5955. Min Act: -0.0000

Data Index: 1114421 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 1.0950. Min Range: -1.0950

Max Act: 0.5872. Min Act: -0.0000

Data Index: 1033043 (C4 (Web Text))

Max Activating Token Index: 502

Text #8

Max Range: 1.0950. Min Range: -1.0950

Max Act: 0.5833. Min Act: -0.0001

Data Index: 1192463 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 1.0950. Min Range: -1.0950

Max Act: 0.5811. Min Act: -0.0000

Data Index: 1034380 (C4 (Web Text))

Max Activating Token Index: 53

Text #10

Max Range: 1.0950. Min Range: -1.0950

Max Act: 0.5930. Min Act: -0.0000

Data Index: 400961 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 1.0950. Min Range: -1.0950

Max Act: 0.5931. Min Act: -0.0000

Data Index: 685965 (C4 (Web Text))

Max Activating Token Index: 952

Text #12

Max Range: 1.0950. Min Range: -1.0950

Max Act: 0.5822. Min Act: -0.0000

Data Index: 348626 (C4 (Web Text))

Max Activating Token Index: 358

Text #13

Max Range: 1.0950. Min Range: -1.0950

Max Act: 0.5690. Min Act: -0.0000

Data Index: 433524 (C4 (Web Text))

Max Activating Token Index: 303

Text #14

Max Range: 1.0950. Min Range: -1.0950

Max Act: 0.5974. Min Act: -0.0000

Data Index: 342890 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 1.0950. Min Range: -1.0950

Max Act: 0.5755. Min Act: -0.0000

Data Index: 910767 (C4 (Web Text))

Max Activating Token Index: 869

Text #16

Max Range: 1.0950. Min Range: -1.0950

Max Act: 0.5782. Min Act: -0.0000

Data Index: 225367 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 1.0950. Min Range: -1.0950

Max Act: 0.5712. Min Act: -0.0001

Data Index: 85068 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 1.0950. Min Range: -1.0950

Max Act: 0.5514. Min Act: -0.0000

Data Index: 702957 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 1.0950. Min Range: -1.0950

Max Act: 0.5439. Min Act: -0.0001

Data Index: 823262 (C4 (Web Text))

Max Activating Token Index: 331