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

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

Neuron 3580 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: 0.5783. Min Range: -0.5783

Max Act: 0.5520. Min Act: -0.0001

Data Index: 908655 (C4 (Web Text))

Max Activating Token Index: 785

Text #1

Max Range: 0.5783. Min Range: -0.5783

Max Act: 0.5783. Min Act: -0.0001

Data Index: 32894 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 0.5783. Min Range: -0.5783

Max Act: 0.5487. Min Act: -0.0001

Data Index: 1153987 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 0.5783. Min Range: -0.5783

Max Act: 0.5198. Min Act: -0.0001

Data Index: 481047 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 0.5783. Min Range: -0.5783

Max Act: 0.5542. Min Act: -0.0001

Data Index: 1282389 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 0.5783. Min Range: -0.5783

Max Act: 0.5304. Min Act: -0.0001

Data Index: 755742 (C4 (Web Text))

Max Activating Token Index: 760

Text #6

Max Range: 0.5783. Min Range: -0.5783

Max Act: 0.4424. Min Act: -0.0001

Data Index: 593049 (C4 (Web Text))

Max Activating Token Index: 981

Text #7

Max Range: 0.5783. Min Range: -0.5783

Max Act: 0.4748. Min Act: -0.0001

Data Index: 552706 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 0.5783. Min Range: -0.5783

Max Act: 0.5031. Min Act: -0.0001

Data Index: 770299 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 0.5783. Min Range: -0.5783

Max Act: 0.4194. Min Act: -0.0001

Data Index: 637682 (C4 (Web Text))

Max Activating Token Index: 810

Text #10

Max Range: 0.5783. Min Range: -0.5783

Max Act: 0.5198. Min Act: -0.0001

Data Index: 961421 (C4 (Web Text))

Max Activating Token Index: 732

Text #11

Max Range: 0.5783. Min Range: -0.5783

Max Act: 0.4739. Min Act: -0.0001

Data Index: 559083 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 0.5783. Min Range: -0.5783

Max Act: 0.4632. Min Act: -0.0001

Data Index: 641054 (C4 (Web Text))

Max Activating Token Index: 216

Text #13

Max Range: 0.5783. Min Range: -0.5783

Max Act: 0.4448. Min Act: -0.0001

Data Index: 441981 (C4 (Web Text))

Max Activating Token Index: 412

Text #14

Max Range: 0.5783. Min Range: -0.5783

Max Act: 0.4761. Min Act: -0.0001

Data Index: 506592 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 0.5783. Min Range: -0.5783

Max Act: 0.4186. Min Act: -0.0001

Data Index: 369919 (C4 (Web Text))

Max Activating Token Index: 149

Text #16

Max Range: 0.5783. Min Range: -0.5783

Max Act: 0.4873. Min Act: -0.0001

Data Index: 311106 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 0.5783. Min Range: -0.5783

Max Act: 0.4398. Min Act: -0.0001

Data Index: 18140 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 0.5783. Min Range: -0.5783

Max Act: 0.4509. Min Act: -0.0001

Data Index: 1279677 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 0.5783. Min Range: -0.5783

Max Act: 0.4488. Min Act: -0.0001

Data Index: 779375 (C4 (Web Text))

Max Activating Token Index: 933