Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2778 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.3221. Min Act: -0.0003

Data Index: 1101767 (C4 (Web Text))

Max Activating Token Index: 385

Text #1

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2901. Min Act: -0.0003

Data Index: 391675 (C4 (Web Text))

Max Activating Token Index: 657

Text #2

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.3010. Min Act: -0.0003

Data Index: 154047 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2900. Min Act: -0.0003

Data Index: 992563 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2921. Min Act: -0.0003

Data Index: 127050 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2961. Min Act: -0.0003

Data Index: 794760 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2878. Min Act: -0.0003

Data Index: 1252991 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2863. Min Act: -0.0003

Data Index: 622687 (C4 (Web Text))

Max Activating Token Index: 490

Text #8

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2672. Min Act: -0.0003

Data Index: 1108094 (C4 (Web Text))

Max Activating Token Index: 898

Text #9

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2649. Min Act: -0.0003

Data Index: 533186 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2824. Min Act: -0.0003

Data Index: 1020899 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2889. Min Act: -0.0003

Data Index: 1190084 (C4 (Web Text))

Max Activating Token Index: 993

Text #12

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2710. Min Act: -0.0003

Data Index: 943716 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2783. Min Act: -0.0003

Data Index: 1270078 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2687. Min Act: -0.0003

Data Index: 670693 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2723. Min Act: -0.0003

Data Index: 809231 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2834. Min Act: -0.0003

Data Index: 726031 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2559. Min Act: -0.0003

Data Index: 230117 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2894. Min Act: -0.0003

Data Index: 1002075 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2417. Min Act: -0.0003

Data Index: 1357427 (C4 (Web Text))

Max Activating Token Index: 679