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

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

Neuron 4812 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0560. Min Range: -1.0560

Max Act: 1.0560. Min Act: -0.0001

Data Index: 1175710 (C4 (Web Text))

Max Activating Token Index: 305

Text #1

Max Range: 1.0560. Min Range: -1.0560

Max Act: 1.0277. Min Act: -0.0000

Data Index: 1291893 (C4 (Web Text))

Max Activating Token Index: 741

Text #2

Max Range: 1.0560. Min Range: -1.0560

Max Act: 1.0175. Min Act: -0.0000

Data Index: 442675 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.9504. Min Act: -0.0000

Data Index: 827160 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.8758. Min Act: -0.0000

Data Index: 460457 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.8401. Min Act: -0.0000

Data Index: 164775 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.8653. Min Act: -0.0000

Data Index: 568827 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.8357. Min Act: -0.0000

Data Index: 1045376 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.9070. Min Act: -0.0001

Data Index: 1155465 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.9228. Min Act: -0.0000

Data Index: 211162 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.9245. Min Act: -0.0000

Data Index: 491184 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.8697. Min Act: -0.0000

Data Index: 769650 (C4 (Web Text))

Max Activating Token Index: 13

Text #12

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.9132. Min Act: -0.0000

Data Index: 336075 (C4 (Web Text))

Max Activating Token Index: 226

Text #13

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.9267. Min Act: -0.0000

Data Index: 891356 (C4 (Web Text))

Max Activating Token Index: 804

Text #14

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.8680. Min Act: -0.0000

Data Index: 666545 (C4 (Web Text))

Max Activating Token Index: 314

Text #15

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.8387. Min Act: -0.0000

Data Index: 945101 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.8632. Min Act: -0.0000

Data Index: 427447 (C4 (Web Text))

Max Activating Token Index: 587

Text #17

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.7899. Min Act: -0.0001

Data Index: 315637 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.8406. Min Act: -0.0001

Data Index: 1280324 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 1.0560. Min Range: -1.0560

Max Act: 0.8167. Min Act: -0.0000

Data Index: 514434 (C4 (Web Text))

Max Activating Token Index: 934