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

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

Neuron 152 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: 1.0044. Min Range: -1.0044

Max Act: 0.9709. Min Act: -0.0001

Data Index: 1170580 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 1.0044. Min Range: -1.0044

Max Act: 0.9831. Min Act: -0.0001

Data Index: 353667 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 1.0044. Min Range: -1.0044

Max Act: 0.9815. Min Act: -0.0001

Data Index: 785450 (C4 (Web Text))

Max Activating Token Index: 659

Text #3

Max Range: 1.0044. Min Range: -1.0044

Max Act: 1.0044. Min Act: -0.0001

Data Index: 911768 (C4 (Web Text))

Max Activating Token Index: 302

Text #4

Max Range: 1.0044. Min Range: -1.0044

Max Act: 0.9841. Min Act: -0.0001

Data Index: 42026 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 1.0044. Min Range: -1.0044

Max Act: 0.8755. Min Act: -0.0001

Data Index: 175267 (C4 (Web Text))

Max Activating Token Index: 230

Text #6

Max Range: 1.0044. Min Range: -1.0044

Max Act: 0.8932. Min Act: -0.0001

Data Index: 73802 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 1.0044. Min Range: -1.0044

Max Act: 0.8707. Min Act: -0.0001

Data Index: 1086600 (C4 (Web Text))

Max Activating Token Index: 516

Text #8

Max Range: 1.0044. Min Range: -1.0044

Max Act: 0.8599. Min Act: -0.0001

Data Index: 747059 (C4 (Web Text))

Max Activating Token Index: 795

Text #9

Max Range: 1.0044. Min Range: -1.0044

Max Act: 0.7565. Min Act: -0.0001

Data Index: 466839 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 1.0044. Min Range: -1.0044

Max Act: 0.7558. Min Act: -0.0001

Data Index: 216865 (C4 (Web Text))

Max Activating Token Index: 666

Text #11

Max Range: 1.0044. Min Range: -1.0044

Max Act: 0.7935. Min Act: -0.0001

Data Index: 1204377 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 1.0044. Min Range: -1.0044

Max Act: 0.7902. Min Act: -0.0001

Data Index: 1352426 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 1.0044. Min Range: -1.0044

Max Act: 0.7349. Min Act: -0.0001

Data Index: 15153 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 1.0044. Min Range: -1.0044

Max Act: 0.7036. Min Act: -0.0001

Data Index: 723993 (C4 (Web Text))

Max Activating Token Index: 583

Text #15

Max Range: 1.0044. Min Range: -1.0044

Max Act: 0.6995. Min Act: -0.0001

Data Index: 647361 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 1.0044. Min Range: -1.0044

Max Act: 0.6809. Min Act: -0.0001

Data Index: 770556 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 1.0044. Min Range: -1.0044

Max Act: 0.7419. Min Act: -0.0001

Data Index: 608561 (C4 (Web Text))

Max Activating Token Index: 672

Text #18

Max Range: 1.0044. Min Range: -1.0044

Max Act: 0.6525. Min Act: -0.0001

Data Index: 323342 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 1.0044. Min Range: -1.0044

Max Act: 0.6715. Min Act: -0.0001

Data Index: 297966 (C4 (Web Text))

Max Activating Token Index: 181