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

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

Neuron 5040 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.7615. Min Act: -0.0000

Data Index: 677029 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.7592. Min Act: -0.0000

Data Index: 253229 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6207. Min Act: -0.0000

Data Index: 20355 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.5967. Min Act: -0.0000

Data Index: 568813 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.6502. Min Act: -0.0000

Data Index: 555394 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.5134. Min Act: -0.0000

Data Index: 1155455 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.4963. Min Act: -0.0000

Data Index: 1342112 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.4112. Min Act: -0.0000

Data Index: 399962 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.3936. Min Act: -0.0000

Data Index: 1069099 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.4738. Min Act: -0.0000

Data Index: 309937 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.4662. Min Act: -0.0000

Data Index: 656683 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.3483. Min Act: -0.0000

Data Index: 1047528 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.2628. Min Act: -0.0000

Data Index: 822827 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.4124. Min Act: -0.0000

Data Index: 965435 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.2526. Min Act: -0.0000

Data Index: 109824 (C4 (Web Text))

Max Activating Token Index: 800

Text #15

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.3346. Min Act: -0.0000

Data Index: 128051 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.3944. Min Act: -0.0000

Data Index: 781042 (C4 (Web Text))

Max Activating Token Index: 891

Text #17

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.4062. Min Act: -0.0000

Data Index: 450666 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.2995. Min Act: -0.0000

Data Index: 744129 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 1.7615. Min Range: -1.7615

Max Act: 1.3894. Min Act: -0.0000

Data Index: 1095226 (C4 (Web Text))

Max Activating Token Index: 942