Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 241 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1580. Min Range: -1.1580

Max Act: 1.1580. Min Act: -0.0001

Data Index: 756285 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 1.1580. Min Range: -1.1580

Max Act: 1.0754. Min Act: -0.0001

Data Index: 1212977 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 1.1580. Min Range: -1.1580

Max Act: 1.0766. Min Act: -0.0001

Data Index: 1310771 (C4 (Web Text))

Max Activating Token Index: 590

Text #3

Max Range: 1.1580. Min Range: -1.1580

Max Act: 1.0010. Min Act: -0.0001

Data Index: 125441 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.9920. Min Act: -0.0001

Data Index: 854902 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.9076. Min Act: -0.0001

Data Index: 819375 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.8926. Min Act: -0.0001

Data Index: 1176579 (C4 (Web Text))

Max Activating Token Index: 973

Text #7

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.9485. Min Act: -0.0001

Data Index: 140280 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.9221. Min Act: -0.0001

Data Index: 1248873 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.9298. Min Act: -0.0001

Data Index: 343631 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.8825. Min Act: -0.0001

Data Index: 882502 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.8747. Min Act: -0.0001

Data Index: 907365 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.8501. Min Act: -0.0001

Data Index: 44717 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.8966. Min Act: -0.0001

Data Index: 340038 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.8035. Min Act: -0.0001

Data Index: 962664 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.8458. Min Act: -0.0001

Data Index: 291077 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.8317. Min Act: -0.0001

Data Index: 639835 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.8349. Min Act: -0.0001

Data Index: 621312 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.7985. Min Act: -0.0001

Data Index: 703132 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 1.1580. Min Range: -1.1580

Max Act: 0.8218. Min Act: -0.0001

Data Index: 372979 (C4 (Web Text))

Max Activating Token Index: 799