Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4208 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6811. Min Range: -0.6811

Max Act: 0.6811. Min Act: -0.0000

Data Index: 394013 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 0.6811. Min Range: -0.6811

Max Act: 0.6488. Min Act: -0.0000

Data Index: 455715 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 0.6811. Min Range: -0.6811

Max Act: 0.6587. Min Act: -0.0000

Data Index: 798397 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 0.6811. Min Range: -0.6811

Max Act: 0.5771. Min Act: -0.0000

Data Index: 1359026 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 0.6811. Min Range: -0.6811

Max Act: 0.6014. Min Act: -0.0000

Data Index: 451544 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 0.6811. Min Range: -0.6811

Max Act: 0.5695. Min Act: -0.0000

Data Index: 441034 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 0.6811. Min Range: -0.6811

Max Act: 0.5664. Min Act: -0.0000

Data Index: 789777 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 0.6811. Min Range: -0.6811

Max Act: 0.5579. Min Act: -0.0000

Data Index: 310350 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 0.6811. Min Range: -0.6811

Max Act: 0.5138. Min Act: -0.0000

Data Index: 595974 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 0.6811. Min Range: -0.6811

Max Act: 0.4717. Min Act: -0.0000

Data Index: 633547 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 0.6811. Min Range: -0.6811

Max Act: 0.5036. Min Act: -0.0000

Data Index: 1053589 (C4 (Web Text))

Max Activating Token Index: 458

Text #11

Max Range: 0.6811. Min Range: -0.6811

Max Act: 0.5024. Min Act: -0.0000

Data Index: 1092000 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 0.6811. Min Range: -0.6811

Max Act: 0.5109. Min Act: -0.0000

Data Index: 669600 (C4 (Web Text))

Max Activating Token Index: 982

Text #13

Max Range: 0.6811. Min Range: -0.6811

Max Act: 0.4950. Min Act: -0.0000

Data Index: 751189 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 0.6811. Min Range: -0.6811

Max Act: 0.5096. Min Act: -0.0000

Data Index: 564439 (C4 (Web Text))

Max Activating Token Index: 966

Text #15

Max Range: 0.6811. Min Range: -0.6811

Max Act: 0.4982. Min Act: -0.0000

Data Index: 512384 (C4 (Web Text))

Max Activating Token Index: 917

Text #16

Max Range: 0.6811. Min Range: -0.6811

Max Act: 0.4858. Min Act: -0.0000

Data Index: 1083089 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 0.6811. Min Range: -0.6811

Max Act: 0.4829. Min Act: -0.0000

Data Index: 445745 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 0.6811. Min Range: -0.6811

Max Act: 0.4788. Min Act: -0.0000

Data Index: 1323427 (C4 (Web Text))

Max Activating Token Index: 292

Text #19

Max Range: 0.6811. Min Range: -0.6811

Max Act: 0.5105. Min Act: -0.0000

Data Index: 1349108 (C4 (Web Text))

Max Activating Token Index: 336