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

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

Neuron 3225 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0230. Min Range: -1.0230

Max Act: 1.0230. Min Act: -0.0001

Data Index: 343166 (C4 (Web Text))

Max Activating Token Index: 909

Text #1

Max Range: 1.0230. Min Range: -1.0230

Max Act: 0.7730. Min Act: -0.0001

Data Index: 511803 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 1.0230. Min Range: -1.0230

Max Act: 0.9040. Min Act: -0.0001

Data Index: 1246057 (C4 (Web Text))

Max Activating Token Index: 635

Text #3

Max Range: 1.0230. Min Range: -1.0230

Max Act: 0.7503. Min Act: -0.0001

Data Index: 1339278 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 1.0230. Min Range: -1.0230

Max Act: 0.6969. Min Act: -0.0001

Data Index: 1135202 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 1.0230. Min Range: -1.0230

Max Act: 0.7826. Min Act: -0.0001

Data Index: 723167 (C4 (Web Text))

Max Activating Token Index: 101

Text #6

Max Range: 1.0230. Min Range: -1.0230

Max Act: 0.6711. Min Act: -0.0001

Data Index: 591830 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 1.0230. Min Range: -1.0230

Max Act: 0.7109. Min Act: -0.0001

Data Index: 163224 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 1.0230. Min Range: -1.0230

Max Act: 0.6993. Min Act: -0.0001

Data Index: 162157 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 1.0230. Min Range: -1.0230

Max Act: 0.6542. Min Act: -0.0001

Data Index: 1339739 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 1.0230. Min Range: -1.0230

Max Act: 0.6454. Min Act: -0.0001

Data Index: 725011 (C4 (Web Text))

Max Activating Token Index: 975

Text #11

Max Range: 1.0230. Min Range: -1.0230

Max Act: 0.6742. Min Act: -0.0001

Data Index: 613880 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 1.0230. Min Range: -1.0230

Max Act: 0.7137. Min Act: -0.0001

Data Index: 636025 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 1.0230. Min Range: -1.0230

Max Act: 0.6293. Min Act: -0.0001

Data Index: 145592 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 1.0230. Min Range: -1.0230

Max Act: 0.6836. Min Act: -0.0001

Data Index: 989638 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 1.0230. Min Range: -1.0230

Max Act: 0.6759. Min Act: -0.0001

Data Index: 1325242 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 1.0230. Min Range: -1.0230

Max Act: 0.6540. Min Act: -0.0001

Data Index: 1306409 (C4 (Web Text))

Max Activating Token Index: 223

Text #17

Max Range: 1.0230. Min Range: -1.0230

Max Act: 0.6732. Min Act: -0.0001

Data Index: 960980 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 1.0230. Min Range: -1.0230

Max Act: 0.6362. Min Act: -0.0001

Data Index: 551129 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 1.0230. Min Range: -1.0230

Max Act: 0.6676. Min Act: -0.0001

Data Index: 220765 (C4 (Web Text))

Max Activating Token Index: 845