Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 38 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.7831. Min Range: -0.7831
Max Act: 0.6999. Min Act: -0.0001
Data Index: 1457877 (Python Code)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7831. Min Range: -0.7831
Max Act: 0.7181. Min Act: -0.0001
Data Index: 1040940 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7831. Min Range: -0.7831
Max Act: 0.6999. Min Act: -0.0001
Data Index: 1162967 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7831. Min Range: -0.7831
Max Act: 0.7246. Min Act: -0.0001
Data Index: 393405 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7831. Min Range: -0.7831
Max Act: 0.6834. Min Act: -0.0001
Data Index: 1628073 (Python Code)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7831. Min Range: -0.7831
Max Act: 0.6793. Min Act: -0.0001
Data Index: 798847 (C4 (Web Text))
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7831. Min Range: -0.7831
Max Act: 0.7831. Min Act: -0.0001
Data Index: 995832 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7831. Min Range: -0.7831
Max Act: 0.7018. Min Act: -0.0001
Data Index: 1453921 (Python Code)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7831. Min Range: -0.7831
Max Act: 0.6995. Min Act: -0.0001
Data Index: 765554 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7831. Min Range: -0.7831
Max Act: 0.6707. Min Act: -0.0001
Data Index: 873592 (C4 (Web Text))
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7831. Min Range: -0.7831
Max Act: 0.6690. Min Act: -0.0001
Data Index: 1186977 (C4 (Web Text))
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7831. Min Range: -0.7831
Max Act: 0.6363. Min Act: -0.0001
Data Index: 1463082 (Python Code)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7831. Min Range: -0.7831
Max Act: 0.6114. Min Act: -0.0001
Data Index: 1584361 (Python Code)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7831. Min Range: -0.7831
Max Act: 0.6146. Min Act: -0.0001
Data Index: 847747 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7831. Min Range: -0.7831
Max Act: 0.6446. Min Act: -0.0001
Data Index: 1100854 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7831. Min Range: -0.7831
Max Act: 0.6638. Min Act: -0.0001
Data Index: 941601 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7831. Min Range: -0.7831
Max Act: 0.6243. Min Act: -0.0001
Data Index: 709756 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7831. Min Range: -0.7831
Max Act: 0.6085. Min Act: -0.0001
Data Index: 735882 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7831. Min Range: -0.7831
Max Act: 0.6221. Min Act: -0.0001
Data Index: 1009616 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7831. Min Range: -0.7831
Max Act: 0.6075. Min Act: -0.0001
Data Index: 208541 (C4 (Web Text))
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #19