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

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

Neuron 664 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4787. Min Range: -1.4787

Max Act: 1.4787. Min Act: -0.0000

Data Index: 27256 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 1.4787. Min Range: -1.4787

Max Act: 1.3603. Min Act: -0.0000

Data Index: 24118 (C4 (Web Text))

Max Activating Token Index: 317

Text #2

Max Range: 1.4787. Min Range: -1.4787

Max Act: 1.1629. Min Act: -0.0000

Data Index: 165179 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 1.4787. Min Range: -1.4787

Max Act: 1.0043. Min Act: -0.0000

Data Index: 481844 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 1.4787. Min Range: -1.4787

Max Act: 1.0908. Min Act: -0.0000

Data Index: 479963 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 1.4787. Min Range: -1.4787

Max Act: 1.2009. Min Act: -0.0000

Data Index: 655134 (C4 (Web Text))

Max Activating Token Index: 233

Text #6

Max Range: 1.4787. Min Range: -1.4787

Max Act: 0.7047. Min Act: -0.0000

Data Index: 5505 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 1.4787. Min Range: -1.4787

Max Act: 1.0954. Min Act: -0.0000

Data Index: 226662 (C4 (Web Text))

Max Activating Token Index: 866

Text #8

Max Range: 1.4787. Min Range: -1.4787

Max Act: 1.0713. Min Act: -0.0000

Data Index: 836476 (C4 (Web Text))

Max Activating Token Index: 893

Text #9

Max Range: 1.4787. Min Range: -1.4787

Max Act: 1.0045. Min Act: -0.0000

Data Index: 81139 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 1.4787. Min Range: -1.4787

Max Act: 1.0845. Min Act: -0.0000

Data Index: 694108 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 1.4787. Min Range: -1.4787

Max Act: 1.0045. Min Act: -0.0000

Data Index: 546248 (C4 (Web Text))

Max Activating Token Index: 559

Text #12

Max Range: 1.4787. Min Range: -1.4787

Max Act: 1.0349. Min Act: -0.0000

Data Index: 126676 (C4 (Web Text))

Max Activating Token Index: 637

Text #13

Max Range: 1.4787. Min Range: -1.4787

Max Act: 0.9340. Min Act: -0.0000

Data Index: 74890 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 1.4787. Min Range: -1.4787

Max Act: 0.9562. Min Act: -0.0000

Data Index: 1214092 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 1.4787. Min Range: -1.4787

Max Act: 0.9232. Min Act: -0.0000

Data Index: 1119693 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 1.4787. Min Range: -1.4787

Max Act: 0.9131. Min Act: -0.0000

Data Index: 89339 (C4 (Web Text))

Max Activating Token Index: 1021

Text #17

Max Range: 1.4787. Min Range: -1.4787

Max Act: 0.9286. Min Act: -0.0000

Data Index: 897554 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 1.4787. Min Range: -1.4787

Max Act: 0.9347. Min Act: -0.0000

Data Index: 1218961 (C4 (Web Text))

Max Activating Token Index: 828

Text #19

Max Range: 1.4787. Min Range: -1.4787

Max Act: 0.9143. Min Act: -0.0000

Data Index: 1294396 (C4 (Web Text))

Max Activating Token Index: 36