Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5536 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.9389. Min Range: -0.9389

Max Act: 0.9389. Min Act: -0.0001

Data Index: 896488 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 0.9389. Min Range: -0.9389

Max Act: 0.8715. Min Act: -0.0001

Data Index: 661799 (C4 (Web Text))

Max Activating Token Index: 189

Text #2

Max Range: 0.9389. Min Range: -0.9389

Max Act: 0.8605. Min Act: -0.0001

Data Index: 979695 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 0.9389. Min Range: -0.9389

Max Act: 0.8139. Min Act: -0.0001

Data Index: 665389 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 0.9389. Min Range: -0.9389

Max Act: 0.8181. Min Act: -0.0001

Data Index: 1113510 (C4 (Web Text))

Max Activating Token Index: 446

Text #5

Max Range: 0.9389. Min Range: -0.9389

Max Act: 0.8030. Min Act: -0.0001

Data Index: 229650 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 0.9389. Min Range: -0.9389

Max Act: 0.8311. Min Act: -0.0001

Data Index: 210399 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 0.9389. Min Range: -0.9389

Max Act: 0.8019. Min Act: -0.0001

Data Index: 694804 (C4 (Web Text))

Max Activating Token Index: 284

Text #8

Max Range: 0.9389. Min Range: -0.9389

Max Act: 0.7905. Min Act: -0.0001

Data Index: 1094664 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 0.9389. Min Range: -0.9389

Max Act: 0.8056. Min Act: -0.0001

Data Index: 757585 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 0.9389. Min Range: -0.9389

Max Act: 0.8125. Min Act: -0.0001

Data Index: 1099000 (C4 (Web Text))

Max Activating Token Index: 407

Text #11

Max Range: 0.9389. Min Range: -0.9389

Max Act: 0.8000. Min Act: -0.0001

Data Index: 262606 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 0.9389. Min Range: -0.9389

Max Act: 0.7848. Min Act: -0.0001

Data Index: 217279 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 0.9389. Min Range: -0.9389

Max Act: 0.7835. Min Act: -0.0001

Data Index: 830691 (C4 (Web Text))

Max Activating Token Index: 571

Text #14

Max Range: 0.9389. Min Range: -0.9389

Max Act: 0.7775. Min Act: -0.0001

Data Index: 243445 (C4 (Web Text))

Max Activating Token Index: 721

Text #15

Max Range: 0.9389. Min Range: -0.9389

Max Act: 0.8091. Min Act: -0.0001

Data Index: 493135 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 0.9389. Min Range: -0.9389

Max Act: 0.7747. Min Act: -0.0001

Data Index: 834857 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 0.9389. Min Range: -0.9389

Max Act: 0.8093. Min Act: -0.0001

Data Index: 816571 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 0.9389. Min Range: -0.9389

Max Act: 0.7798. Min Act: -0.0001

Data Index: 593105 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 0.9389. Min Range: -0.9389

Max Act: 0.7863. Min Act: -0.0001

Data Index: 1312817 (C4 (Web Text))

Max Activating Token Index: 385