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

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

Neuron 180 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0976. Min Range: -1.0976

Max Act: 1.0976. Min Act: -0.0001

Data Index: 320027 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 1.0976. Min Range: -1.0976

Max Act: 0.9458. Min Act: -0.0001

Data Index: 307585 (C4 (Web Text))

Max Activating Token Index: 898

Text #2

Max Range: 1.0976. Min Range: -1.0976

Max Act: 0.9361. Min Act: -0.0001

Data Index: 467898 (C4 (Web Text))

Max Activating Token Index: 839

Text #3

Max Range: 1.0976. Min Range: -1.0976

Max Act: 0.9153. Min Act: -0.0001

Data Index: 1161350 (C4 (Web Text))

Max Activating Token Index: 275

Text #4

Max Range: 1.0976. Min Range: -1.0976

Max Act: 0.8422. Min Act: -0.0001

Data Index: 529865 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 1.0976. Min Range: -1.0976

Max Act: 0.7746. Min Act: -0.0001

Data Index: 713837 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 1.0976. Min Range: -1.0976

Max Act: 0.7389. Min Act: -0.0001

Data Index: 875659 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 1.0976. Min Range: -1.0976

Max Act: 0.7264. Min Act: -0.0001

Data Index: 1339682 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 1.0976. Min Range: -1.0976

Max Act: 0.7018. Min Act: -0.0001

Data Index: 164343 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 1.0976. Min Range: -1.0976

Max Act: 0.6987. Min Act: -0.0001

Data Index: 641617 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 1.0976. Min Range: -1.0976

Max Act: 0.7045. Min Act: -0.0001

Data Index: 1300504 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 1.0976. Min Range: -1.0976

Max Act: 0.6812. Min Act: -0.0001

Data Index: 186679 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 1.0976. Min Range: -1.0976

Max Act: 0.6964. Min Act: -0.0001

Data Index: 445475 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 1.0976. Min Range: -1.0976

Max Act: 0.7007. Min Act: -0.0001

Data Index: 1353446 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 1.0976. Min Range: -1.0976

Max Act: 0.6374. Min Act: -0.0001

Data Index: 1346920 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 1.0976. Min Range: -1.0976

Max Act: 0.6159. Min Act: -0.0001

Data Index: 666341 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 1.0976. Min Range: -1.0976

Max Act: 0.6490. Min Act: -0.0001

Data Index: 793573 (C4 (Web Text))

Max Activating Token Index: 325

Text #17

Max Range: 1.0976. Min Range: -1.0976

Max Act: 0.6822. Min Act: -0.0001

Data Index: 962763 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 1.0976. Min Range: -1.0976

Max Act: 0.6105. Min Act: -0.0001

Data Index: 248089 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 1.0976. Min Range: -1.0976

Max Act: 0.7055. Min Act: -0.0001

Data Index: 465929 (C4 (Web Text))

Max Activating Token Index: 634