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

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

Neuron 1364 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.9861. Min Act: -0.0001

Data Index: 1343235 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.8065. Min Act: -0.0001

Data Index: 668104 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.8362. Min Act: -0.0001

Data Index: 1088434 (C4 (Web Text))

Max Activating Token Index: 878

Text #3

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.8491. Min Act: -0.0001

Data Index: 198795 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.7603. Min Act: -0.0001

Data Index: 1100790 (C4 (Web Text))

Max Activating Token Index: 808

Text #5

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.6866. Min Act: -0.0001

Data Index: 587571 (C4 (Web Text))

Max Activating Token Index: 100

Text #6

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.6384. Min Act: -0.0001

Data Index: 9577 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.5058. Min Act: -0.0001

Data Index: 1357887 (C4 (Web Text))

Max Activating Token Index: 276

Text #8

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.5562. Min Act: -0.0001

Data Index: 218916 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.7191. Min Act: -0.0001

Data Index: 598085 (C4 (Web Text))

Max Activating Token Index: 449

Text #10

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.5127. Min Act: -0.0001

Data Index: 1168157 (C4 (Web Text))

Max Activating Token Index: 599

Text #11

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.5436. Min Act: -0.0001

Data Index: 641617 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.6034. Min Act: -0.0001

Data Index: 550763 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.6265. Min Act: -0.0001

Data Index: 646570 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.5959. Min Act: -0.0001

Data Index: 770514 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.7359. Min Act: -0.0001

Data Index: 1333374 (C4 (Web Text))

Max Activating Token Index: 582

Text #16

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.6108. Min Act: -0.0001

Data Index: 835445 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.4702. Min Act: -0.0001

Data Index: 601007 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.5855. Min Act: -0.0001

Data Index: 1246905 (C4 (Web Text))

Max Activating Token Index: 627

Text #19

Max Range: 0.9861. Min Range: -0.9861

Max Act: 0.7014. Min Act: -0.0001

Data Index: 672298 (C4 (Web Text))

Max Activating Token Index: 792