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

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

Neuron 4089 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: 0.9196. Min Range: -0.9196

Max Act: 0.9196. Min Act: -0.0001

Data Index: 1137621 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.8723. Min Act: -0.0001

Data Index: 26236 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.8354. Min Act: -0.0001

Data Index: 237993 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.8488. Min Act: -0.0001

Data Index: 229928 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.7992. Min Act: -0.0001

Data Index: 861075 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.8042. Min Act: -0.0002

Data Index: 967387 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.7842. Min Act: -0.0001

Data Index: 37346 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.7518. Min Act: -0.0001

Data Index: 1322869 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.7554. Min Act: -0.0001

Data Index: 326694 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.7434. Min Act: -0.0001

Data Index: 815586 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.7388. Min Act: -0.0001

Data Index: 49088 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.7363. Min Act: -0.0001

Data Index: 359506 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.7490. Min Act: -0.0001

Data Index: 419622 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.7419. Min Act: -0.0001

Data Index: 57060 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.7279. Min Act: -0.0001

Data Index: 1270035 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.7141. Min Act: -0.0001

Data Index: 708328 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.7132. Min Act: -0.0001

Data Index: 919213 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.7036. Min Act: -0.0001

Data Index: 448010 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.7145. Min Act: -0.0001

Data Index: 1247611 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.9196. Min Range: -0.9196

Max Act: 0.7096. Min Act: -0.0001

Data Index: 1323184 (C4 (Web Text))

Max Activating Token Index: 668