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

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

Neuron 1418 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: 3.4915. Min Range: -3.4915

Max Act: 3.4915. Min Act: -0.0000

Data Index: 695140 (C4 (Web Text))

Max Activating Token Index: 476

Text #1

Max Range: 3.4915. Min Range: -3.4915

Max Act: 3.2486. Min Act: -0.0000

Data Index: 134069 (C4 (Web Text))

Max Activating Token Index: 866

Text #2

Max Range: 3.4915. Min Range: -3.4915

Max Act: 3.1661. Min Act: -0.0000

Data Index: 637621 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 3.4915. Min Range: -3.4915

Max Act: 3.0791. Min Act: -0.0000

Data Index: 458224 (C4 (Web Text))

Max Activating Token Index: 986

Text #4

Max Range: 3.4915. Min Range: -3.4915

Max Act: 3.1720. Min Act: -0.0000

Data Index: 1351929 (C4 (Web Text))

Max Activating Token Index: 344

Text #5

Max Range: 3.4915. Min Range: -3.4915

Max Act: 3.0308. Min Act: -0.0000

Data Index: 702955 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 3.4915. Min Range: -3.4915

Max Act: 2.8802. Min Act: -0.0000

Data Index: 1122371 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 3.4915. Min Range: -3.4915

Max Act: 2.9727. Min Act: -0.0000

Data Index: 1261749 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 3.4915. Min Range: -3.4915

Max Act: 2.9787. Min Act: -0.0000

Data Index: 154731 (C4 (Web Text))

Max Activating Token Index: 960

Text #9

Max Range: 3.4915. Min Range: -3.4915

Max Act: 2.9427. Min Act: -0.0000

Data Index: 286344 (C4 (Web Text))

Max Activating Token Index: 935

Text #10

Max Range: 3.4915. Min Range: -3.4915

Max Act: 3.1009. Min Act: -0.0000

Data Index: 346756 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 3.4915. Min Range: -3.4915

Max Act: 2.9518. Min Act: -0.0000

Data Index: 973075 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 3.4915. Min Range: -3.4915

Max Act: 2.9236. Min Act: -0.0000

Data Index: 764882 (C4 (Web Text))

Max Activating Token Index: 925

Text #13

Max Range: 3.4915. Min Range: -3.4915

Max Act: 2.7992. Min Act: -0.0000

Data Index: 662928 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 3.4915. Min Range: -3.4915

Max Act: 2.7404. Min Act: -0.0000

Data Index: 207187 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 3.4915. Min Range: -3.4915

Max Act: 2.7343. Min Act: -0.0000

Data Index: 243325 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 3.4915. Min Range: -3.4915

Max Act: 2.8780. Min Act: -0.0000

Data Index: 684927 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 3.4915. Min Range: -3.4915

Max Act: 2.7300. Min Act: -0.0000

Data Index: 1323341 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 3.4915. Min Range: -3.4915

Max Act: 2.6127. Min Act: -0.0000

Data Index: 192542 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 3.4915. Min Range: -3.4915

Max Act: 2.7339. Min Act: -0.0000

Data Index: 633822 (C4 (Web Text))

Max Activating Token Index: 46