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

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

Neuron 1574 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: 0.5094. Min Range: -0.5094

Max Act: 0.5094. Min Act: -0.0001

Data Index: 544040 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.4829. Min Act: -0.0002

Data Index: 804601 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.4919. Min Act: -0.0001

Data Index: 1071784 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.4750. Min Act: -0.0002

Data Index: 636457 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.4692. Min Act: -0.0001

Data Index: 477835 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.4562. Min Act: -0.0001

Data Index: 1332001 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.4559. Min Act: -0.0001

Data Index: 756376 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.4553. Min Act: -0.0001

Data Index: 978869 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.4495. Min Act: -0.0001

Data Index: 300636 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.4515. Min Act: -0.0001

Data Index: 893702 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.4502. Min Act: -0.0001

Data Index: 955680 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.4491. Min Act: -0.0001

Data Index: 1109778 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.4541. Min Act: -0.0001

Data Index: 972632 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.4496. Min Act: -0.0001

Data Index: 282787 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.4468. Min Act: -0.0001

Data Index: 1295698 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.4541. Min Act: -0.0001

Data Index: 246706 (C4 (Web Text))

Max Activating Token Index: 351

Text #16

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.4533. Min Act: -0.0001

Data Index: 637921 (C4 (Web Text))

Max Activating Token Index: 94

Text #17

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.4575. Min Act: -0.0001

Data Index: 71318 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.4485. Min Act: -0.0001

Data Index: 817924 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 0.5094. Min Range: -0.5094

Max Act: 0.4478. Min Act: -0.0001

Data Index: 1231224 (C4 (Web Text))

Max Activating Token Index: 1023