Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4341 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.7852. Min Range: -0.7852
Max Act: 0.7852. Min Act: -0.0001
Data Index: 828066 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7852. Min Range: -0.7852
Max Act: 0.7566. Min Act: -0.0001
Data Index: 1635625 (Python Code)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7852. Min Range: -0.7852
Max Act: 0.6093. Min Act: -0.0001
Data Index: 1386125 (Python Code)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7852. Min Range: -0.7852
Max Act: 0.6140. Min Act: -0.0001
Data Index: 1593265 (Python Code)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7852. Min Range: -0.7852
Max Act: 0.5870. Min Act: -0.0001
Data Index: 1016789 (C4 (Web Text))
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7852. Min Range: -0.7852
Max Act: 0.5896. Min Act: -0.0001
Data Index: 463827 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7852. Min Range: -0.7852
Max Act: 0.5959. Min Act: -0.0001
Data Index: 1635590 (Python Code)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7852. Min Range: -0.7852
Max Act: 0.6051. Min Act: -0.0001
Data Index: 27667 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7852. Min Range: -0.7852
Max Act: 0.5991. Min Act: -0.0001
Data Index: 1419744 (Python Code)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7852. Min Range: -0.7852
Max Act: 0.5235. Min Act: -0.0001
Data Index: 978874 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7852. Min Range: -0.7852
Max Act: 0.6083. Min Act: -0.0001
Data Index: 566913 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7852. Min Range: -0.7852
Max Act: 0.5698. Min Act: -0.0001
Data Index: 408574 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7852. Min Range: -0.7852
Max Act: 0.5577. Min Act: -0.0001
Data Index: 377504 (C4 (Web Text))
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7852. Min Range: -0.7852
Max Act: 0.5909. Min Act: -0.0001
Data Index: 1153577 (C4 (Web Text))
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7852. Min Range: -0.7852
Max Act: 0.5957. Min Act: -0.0001
Data Index: 1527474 (Python Code)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7852. Min Range: -0.7852
Max Act: 0.5300. Min Act: -0.0001
Data Index: 1619415 (Python Code)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7852. Min Range: -0.7852
Max Act: 0.5789. Min Act: -0.0001
Data Index: 1427032 (Python Code)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7852. Min Range: -0.7852
Max Act: 0.5301. Min Act: -0.0001
Data Index: 303326 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7852. Min Range: -0.7852
Max Act: 0.5761. Min Act: -0.0001
Data Index: 95710 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7852. Min Range: -0.7852
Max Act: 0.5226. Min Act: -0.0001
Data Index: 1603803 (Python Code)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #19