Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 218 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.7032. Min Act: -0.0001

Data Index: 338821 (C4 (Web Text))

Max Activating Token Index: 649

Text #1

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.6034. Min Act: -0.0001

Data Index: 165326 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5925. Min Act: -0.0001

Data Index: 657083 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5979. Min Act: -0.0001

Data Index: 631790 (C4 (Web Text))

Max Activating Token Index: 382

Text #4

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5986. Min Act: -0.0001

Data Index: 722064 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5651. Min Act: -0.0001

Data Index: 1281888 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.6637. Min Act: -0.0001

Data Index: 674643 (C4 (Web Text))

Max Activating Token Index: 648

Text #7

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5771. Min Act: -0.0001

Data Index: 618311 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5585. Min Act: -0.0001

Data Index: 698312 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5814. Min Act: -0.0001

Data Index: 1118886 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5051. Min Act: -0.0001

Data Index: 1237973 (C4 (Web Text))

Max Activating Token Index: 657

Text #11

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5647. Min Act: -0.0001

Data Index: 1172758 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5430. Min Act: -0.0001

Data Index: 664306 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5288. Min Act: -0.0001

Data Index: 446203 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5531. Min Act: -0.0001

Data Index: 1080648 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5323. Min Act: -0.0001

Data Index: 1157963 (C4 (Web Text))

Max Activating Token Index: 634

Text #16

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5339. Min Act: -0.0001

Data Index: 1631956 (Python Code)

Max Activating Token Index: 744

Text #17

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.6020. Min Act: -0.0001

Data Index: 338708 (C4 (Web Text))

Max Activating Token Index: 742

Text #18

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5495. Min Act: -0.0001

Data Index: 49939 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5584. Min Act: -0.0001

Data Index: 709139 (C4 (Web Text))

Max Activating Token Index: 967