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

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

Neuron 3827 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: 0.0217. Min Range: -0.0217

Max Act: 0.0217. Min Act: -0.0001

Data Index: 1414872 (Python Code)

Max Activating Token Index: 12

Text #1

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0204. Min Act: -0.0001

Data Index: 258596 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0205. Min Act: -0.0001

Data Index: 1512781 (Python Code)

Max Activating Token Index: 8

Text #3

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0201. Min Act: -0.0001

Data Index: 910130 (C4 (Web Text))

Max Activating Token Index: 196

Text #4

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0205. Min Act: -0.0001

Data Index: 619660 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0198. Min Act: -0.0001

Data Index: 350790 (C4 (Web Text))

Max Activating Token Index: 995

Text #6

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0197. Min Act: -0.0001

Data Index: 1354326 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0201. Min Act: -0.0001

Data Index: 1297260 (C4 (Web Text))

Max Activating Token Index: 922

Text #8

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0197. Min Act: -0.0001

Data Index: 689542 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0195. Min Act: -0.0001

Data Index: 1351836 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0198. Min Act: -0.0001

Data Index: 67452 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0197. Min Act: -0.0001

Data Index: 840453 (C4 (Web Text))

Max Activating Token Index: 989

Text #12

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0196. Min Act: -0.0001

Data Index: 304679 (C4 (Web Text))

Max Activating Token Index: 253

Text #13

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0195. Min Act: -0.0001

Data Index: 1070794 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0194. Min Act: -0.0001

Data Index: 945614 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0194. Min Act: -0.0001

Data Index: 1442941 (Python Code)

Max Activating Token Index: 7

Text #16

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0196. Min Act: -0.0001

Data Index: 1069924 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0192. Min Act: -0.0001

Data Index: 891551 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0191. Min Act: -0.0001

Data Index: 941322 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0190. Min Act: -0.0001

Data Index: 562321 (C4 (Web Text))

Max Activating Token Index: 981