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

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

Neuron 427 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: 2.8576. Min Range: -2.8576

Max Act: 2.5766. Min Act: -0.0000

Data Index: 1279458 (C4 (Web Text))

Max Activating Token Index: 759

Text #1

Max Range: 2.8576. Min Range: -2.8576

Max Act: 2.8576. Min Act: 0.0000

Data Index: 1257157 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 2.8576. Min Range: -2.8576

Max Act: 2.7748. Min Act: -0.0000

Data Index: 3386 (C4 (Web Text))

Max Activating Token Index: 562

Text #3

Max Range: 2.8576. Min Range: -2.8576

Max Act: 2.7557. Min Act: 0.0000

Data Index: 917588 (C4 (Web Text))

Max Activating Token Index: 449

Text #4

Max Range: 2.8576. Min Range: -2.8576

Max Act: 2.6140. Min Act: -0.0000

Data Index: 1227575 (C4 (Web Text))

Max Activating Token Index: 202

Text #5

Max Range: 2.8576. Min Range: -2.8576

Max Act: 2.5029. Min Act: -0.0000

Data Index: 1228584 (C4 (Web Text))

Max Activating Token Index: 575

Text #6

Max Range: 2.8576. Min Range: -2.8576

Max Act: 2.3952. Min Act: 0.0000

Data Index: 147612 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 2.8576. Min Range: -2.8576

Max Act: 2.1503. Min Act: -0.0000

Data Index: 94982 (C4 (Web Text))

Max Activating Token Index: 704

Text #8

Max Range: 2.8576. Min Range: -2.8576

Max Act: 2.0868. Min Act: -0.0000

Data Index: 271896 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 2.8576. Min Range: -2.8576

Max Act: 2.0747. Min Act: -0.0000

Data Index: 1196219 (C4 (Web Text))

Max Activating Token Index: 806

Text #10

Max Range: 2.8576. Min Range: -2.8576

Max Act: 1.9252. Min Act: -0.0000

Data Index: 570614 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 2.8576. Min Range: -2.8576

Max Act: 1.8258. Min Act: -0.0000

Data Index: 449727 (C4 (Web Text))

Max Activating Token Index: 559

Text #12

Max Range: 2.8576. Min Range: -2.8576

Max Act: 1.7683. Min Act: -0.0000

Data Index: 1046230 (C4 (Web Text))

Max Activating Token Index: 885

Text #13

Max Range: 2.8576. Min Range: -2.8576

Max Act: 1.9541. Min Act: -0.0000

Data Index: 1260050 (C4 (Web Text))

Max Activating Token Index: 672

Text #14

Max Range: 2.8576. Min Range: -2.8576

Max Act: 1.8351. Min Act: -0.0000

Data Index: 440856 (C4 (Web Text))

Max Activating Token Index: 420

Text #15

Max Range: 2.8576. Min Range: -2.8576

Max Act: 1.9075. Min Act: -0.0000

Data Index: 172453 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 2.8576. Min Range: -2.8576

Max Act: 2.0086. Min Act: -0.0000

Data Index: 440652 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 2.8576. Min Range: -2.8576

Max Act: 1.8080. Min Act: -0.0000

Data Index: 394465 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 2.8576. Min Range: -2.8576

Max Act: 1.7035. Min Act: -0.0000

Data Index: 760763 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 2.8576. Min Range: -2.8576

Max Act: 1.8316. Min Act: 0.0000

Data Index: 181760 (C4 (Web Text))

Max Activating Token Index: 980