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

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

Neuron 3175 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: 0.7945. Min Range: -0.7945

Max Act: 0.7945. Min Act: -0.0000

Data Index: 1313907 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.7601. Min Act: -0.0001

Data Index: 558233 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6459. Min Act: -0.0001

Data Index: 513651 (C4 (Web Text))

Max Activating Token Index: 979

Text #3

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6781. Min Act: -0.0001

Data Index: 357799 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6422. Min Act: -0.0001

Data Index: 1003855 (C4 (Web Text))

Max Activating Token Index: 983

Text #5

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6127. Min Act: -0.0001

Data Index: 1063855 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6345. Min Act: -0.0000

Data Index: 1593793 (Python Code)

Max Activating Token Index: 34

Text #7

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6287. Min Act: -0.0001

Data Index: 686043 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.5220. Min Act: -0.0000

Data Index: 928903 (C4 (Web Text))

Max Activating Token Index: 59

Text #9

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6066. Min Act: -0.0001

Data Index: 649783 (C4 (Web Text))

Max Activating Token Index: 425

Text #10

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6244. Min Act: -0.0001

Data Index: 1091219 (C4 (Web Text))

Max Activating Token Index: 773

Text #11

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6018. Min Act: -0.0000

Data Index: 197461 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6353. Min Act: -0.0001

Data Index: 262828 (C4 (Web Text))

Max Activating Token Index: 687

Text #13

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.5938. Min Act: -0.0000

Data Index: 318325 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.5845. Min Act: -0.0001

Data Index: 798098 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.5846. Min Act: -0.0000

Data Index: 748025 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.6198. Min Act: -0.0001

Data Index: 314174 (C4 (Web Text))

Max Activating Token Index: 770

Text #17

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.5572. Min Act: -0.0000

Data Index: 877412 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.5794. Min Act: -0.0001

Data Index: 494953 (C4 (Web Text))

Max Activating Token Index: 723

Text #19

Max Range: 0.7945. Min Range: -0.7945

Max Act: 0.5759. Min Act: -0.0001

Data Index: 197251 (C4 (Web Text))

Max Activating Token Index: 40