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

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

Neuron 4482 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: 2.4689. Min Range: -2.4689

Max Act: 2.4689. Min Act: -0.0000

Data Index: 1306237 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 2.4689. Min Range: -2.4689

Max Act: 2.3893. Min Act: -0.0000

Data Index: 245022 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 2.4689. Min Range: -2.4689

Max Act: 2.4402. Min Act: -0.0000

Data Index: 319570 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 2.4689. Min Range: -2.4689

Max Act: 2.1452. Min Act: -0.0000

Data Index: 1004282 (C4 (Web Text))

Max Activating Token Index: 473

Text #4

Max Range: 2.4689. Min Range: -2.4689

Max Act: 2.1582. Min Act: -0.0000

Data Index: 542623 (C4 (Web Text))

Max Activating Token Index: 981

Text #5

Max Range: 2.4689. Min Range: -2.4689

Max Act: 2.0602. Min Act: -0.0000

Data Index: 1261201 (C4 (Web Text))

Max Activating Token Index: 695

Text #6

Max Range: 2.4689. Min Range: -2.4689

Max Act: 2.0239. Min Act: -0.0000

Data Index: 432372 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 2.4689. Min Range: -2.4689

Max Act: 1.9959. Min Act: -0.0000

Data Index: 523608 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 2.4689. Min Range: -2.4689

Max Act: 1.7989. Min Act: -0.0000

Data Index: 438746 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 2.4689. Min Range: -2.4689

Max Act: 2.1063. Min Act: -0.0000

Data Index: 765696 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 2.4689. Min Range: -2.4689

Max Act: 1.9617. Min Act: -0.0000

Data Index: 29209 (C4 (Web Text))

Max Activating Token Index: 631

Text #11

Max Range: 2.4689. Min Range: -2.4689

Max Act: 1.9786. Min Act: -0.0000

Data Index: 142913 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 2.4689. Min Range: -2.4689

Max Act: 2.1828. Min Act: -0.0000

Data Index: 980252 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 2.4689. Min Range: -2.4689

Max Act: 1.9501. Min Act: -0.0000

Data Index: 553004 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 2.4689. Min Range: -2.4689

Max Act: 1.8210. Min Act: -0.0000

Data Index: 63433 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 2.4689. Min Range: -2.4689

Max Act: 2.0431. Min Act: -0.0000

Data Index: 1074988 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 2.4689. Min Range: -2.4689

Max Act: 1.8114. Min Act: -0.0000

Data Index: 672649 (C4 (Web Text))

Max Activating Token Index: 814

Text #17

Max Range: 2.4689. Min Range: -2.4689

Max Act: 1.8979. Min Act: -0.0000

Data Index: 690159 (C4 (Web Text))

Max Activating Token Index: 1002

Text #18

Max Range: 2.4689. Min Range: -2.4689

Max Act: 1.8977. Min Act: -0.0000

Data Index: 1151743 (C4 (Web Text))

Max Activating Token Index: 414

Text #19

Max Range: 2.4689. Min Range: -2.4689

Max Act: 1.9016. Min Act: -0.0000

Data Index: 300610 (C4 (Web Text))

Max Activating Token Index: 220