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

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

Neuron 3578 in Layer 1

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: 2.8550. Min Range: -2.8550

Max Act: 2.8550. Min Act: -0.0002

Data Index: 1084664 (C4 (Web Text))

Max Activating Token Index: 99

Text #1

Max Range: 2.8550. Min Range: -2.8550

Max Act: 2.7997. Min Act: -0.0002

Data Index: 646993 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 2.8550. Min Range: -2.8550

Max Act: 2.8065. Min Act: -0.0002

Data Index: 894864 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 2.8550. Min Range: -2.8550

Max Act: 2.7698. Min Act: -0.0002

Data Index: 1177219 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 2.8550. Min Range: -2.8550

Max Act: 2.6718. Min Act: -0.0002

Data Index: 176540 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 2.8550. Min Range: -2.8550

Max Act: 2.7174. Min Act: -0.0002

Data Index: 428810 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 2.8550. Min Range: -2.8550

Max Act: 2.6448. Min Act: -0.0002

Data Index: 1350513 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 2.8550. Min Range: -2.8550

Max Act: 2.6184. Min Act: -0.0002

Data Index: 1273721 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 2.8550. Min Range: -2.8550

Max Act: 2.6736. Min Act: -0.0002

Data Index: 1219502 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 2.8550. Min Range: -2.8550

Max Act: 2.5656. Min Act: -0.0002

Data Index: 568671 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 2.8550. Min Range: -2.8550

Max Act: 2.6621. Min Act: -0.0002

Data Index: 1219646 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 2.8550. Min Range: -2.8550

Max Act: 2.6195. Min Act: -0.0002

Data Index: 717931 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 2.8550. Min Range: -2.8550

Max Act: 2.5806. Min Act: -0.0002

Data Index: 848174 (C4 (Web Text))

Max Activating Token Index: 999

Text #13

Max Range: 2.8550. Min Range: -2.8550

Max Act: 2.5349. Min Act: -0.0002

Data Index: 960014 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 2.8550. Min Range: -2.8550

Max Act: 2.5454. Min Act: -0.0002

Data Index: 259522 (C4 (Web Text))

Max Activating Token Index: 335

Text #15

Max Range: 2.8550. Min Range: -2.8550

Max Act: 2.5013. Min Act: -0.0002

Data Index: 319090 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 2.8550. Min Range: -2.8550

Max Act: 2.4905. Min Act: -0.0002

Data Index: 260499 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 2.8550. Min Range: -2.8550

Max Act: 2.4872. Min Act: -0.0002

Data Index: 121372 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 2.8550. Min Range: -2.8550

Max Act: 2.5562. Min Act: -0.0002

Data Index: 941052 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 2.8550. Min Range: -2.8550

Max Act: 2.5198. Min Act: -0.0002

Data Index: 1316370 (C4 (Web Text))

Max Activating Token Index: 176