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

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

Neuron 327 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.8036. Min Act: 0.0000

Data Index: 661481 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.8278. Min Act: -0.0000

Data Index: 225999 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.7789. Min Act: -0.0000

Data Index: 37055 (C4 (Web Text))

Max Activating Token Index: 582

Text #3

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.6949. Min Act: -0.0000

Data Index: 627876 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.7001. Min Act: -0.0000

Data Index: 956947 (C4 (Web Text))

Max Activating Token Index: 394

Text #5

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.7383. Min Act: -0.0000

Data Index: 707696 (C4 (Web Text))

Max Activating Token Index: 321

Text #6

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.6944. Min Act: -0.0000

Data Index: 1315651 (C4 (Web Text))

Max Activating Token Index: 457

Text #7

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.7191. Min Act: -0.0000

Data Index: 757567 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.6911. Min Act: -0.0000

Data Index: 512892 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.6713. Min Act: -0.0000

Data Index: 1214825 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.6649. Min Act: -0.0000

Data Index: 234500 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.6555. Min Act: 0.0001

Data Index: 786426 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.6350. Min Act: -0.0000

Data Index: 891835 (C4 (Web Text))

Max Activating Token Index: 749

Text #13

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.6444. Min Act: -0.0000

Data Index: 584385 (C4 (Web Text))

Max Activating Token Index: 804

Text #14

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.6512. Min Act: -0.0000

Data Index: 909671 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.6459. Min Act: -0.0000

Data Index: 956086 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.6830. Min Act: -0.0000

Data Index: 259998 (C4 (Web Text))

Max Activating Token Index: 517

Text #17

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.6595. Min Act: -0.0000

Data Index: 727962 (C4 (Web Text))

Max Activating Token Index: 131

Text #18

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.6558. Min Act: -0.0000

Data Index: 224079 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.6614. Min Act: -0.0000

Data Index: 1252377 (C4 (Web Text))

Max Activating Token Index: 888