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

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

Neuron 3961 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: 0.5791. Min Range: -0.5791

Max Act: 0.5791. Min Act: -0.0001

Data Index: 291158 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 0.5791. Min Range: -0.5791

Max Act: 0.5023. Min Act: -0.0001

Data Index: 1213890 (C4 (Web Text))

Max Activating Token Index: 723

Text #2

Max Range: 0.5791. Min Range: -0.5791

Max Act: 0.4490. Min Act: -0.0001

Data Index: 157576 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 0.5791. Min Range: -0.5791

Max Act: 0.4497. Min Act: -0.0001

Data Index: 493960 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 0.5791. Min Range: -0.5791

Max Act: 0.4252. Min Act: -0.0001

Data Index: 212681 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 0.5791. Min Range: -0.5791

Max Act: 0.4258. Min Act: -0.0001

Data Index: 248185 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 0.5791. Min Range: -0.5791

Max Act: 0.3701. Min Act: -0.0001

Data Index: 253043 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 0.5791. Min Range: -0.5791

Max Act: 0.3743. Min Act: -0.0001

Data Index: 426398 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 0.5791. Min Range: -0.5791

Max Act: 0.3594. Min Act: -0.0001

Data Index: 727973 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 0.5791. Min Range: -0.5791

Max Act: 0.3933. Min Act: -0.0001

Data Index: 680699 (C4 (Web Text))

Max Activating Token Index: 595

Text #10

Max Range: 0.5791. Min Range: -0.5791

Max Act: 0.3813. Min Act: -0.0001

Data Index: 746602 (C4 (Web Text))

Max Activating Token Index: 558

Text #11

Max Range: 0.5791. Min Range: -0.5791

Max Act: 0.3931. Min Act: -0.0001

Data Index: 1225578 (C4 (Web Text))

Max Activating Token Index: 125

Text #12

Max Range: 0.5791. Min Range: -0.5791

Max Act: 0.3717. Min Act: -0.0000

Data Index: 178288 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 0.5791. Min Range: -0.5791

Max Act: 0.3712. Min Act: -0.0001

Data Index: 976895 (C4 (Web Text))

Max Activating Token Index: 334

Text #14

Max Range: 0.5791. Min Range: -0.5791

Max Act: 0.3683. Min Act: -0.0001

Data Index: 649120 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 0.5791. Min Range: -0.5791

Max Act: 0.3354. Min Act: -0.0001

Data Index: 99086 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 0.5791. Min Range: -0.5791

Max Act: 0.3583. Min Act: -0.0001

Data Index: 290002 (C4 (Web Text))

Max Activating Token Index: 920

Text #17

Max Range: 0.5791. Min Range: -0.5791

Max Act: 0.3440. Min Act: -0.0001

Data Index: 904629 (C4 (Web Text))

Max Activating Token Index: 385

Text #18

Max Range: 0.5791. Min Range: -0.5791

Max Act: 0.3647. Min Act: -0.0001

Data Index: 1142707 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 0.5791. Min Range: -0.5791

Max Act: 0.3519. Min Act: -0.0001

Data Index: 655402 (C4 (Web Text))

Max Activating Token Index: 690