Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1999 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.1665. Min Range: -4.1665
Max Act: 4.1040. Min Act: -0.1700
Data Index: 16201 (C4 (Web Text))
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1665. Min Range: -4.1665
Max Act: 4.1665. Min Act: -0.1700
Data Index: 1210579 (C4 (Web Text))
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1665. Min Range: -4.1665
Max Act: 4.1040. Min Act: -0.1700
Data Index: 75296 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1665. Min Range: -4.1665
Max Act: 4.1040. Min Act: -0.1700
Data Index: 478475 (C4 (Web Text))
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1665. Min Range: -4.1665
Max Act: 4.0415. Min Act: -0.1700
Data Index: 863530 (C4 (Web Text))
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1665. Min Range: -4.1665
Max Act: 4.0727. Min Act: -0.1700
Data Index: 387610 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1665. Min Range: -4.1665
Max Act: 3.9789. Min Act: -0.1700
Data Index: 137548 (C4 (Web Text))
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1665. Min Range: -4.1665
Max Act: 4.0102. Min Act: -0.1700
Data Index: 1120401 (C4 (Web Text))
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1665. Min Range: -4.1665
Max Act: 4.0102. Min Act: -0.1700
Data Index: 464644 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1665. Min Range: -4.1665
Max Act: 3.9789. Min Act: -0.1700
Data Index: 723438 (C4 (Web Text))
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1665. Min Range: -4.1665
Max Act: 4.0102. Min Act: -0.1700
Data Index: 1271958 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1665. Min Range: -4.1665
Max Act: 3.9789. Min Act: -0.1700
Data Index: 460325 (C4 (Web Text))
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1665. Min Range: -4.1665
Max Act: 3.9789. Min Act: -0.1700
Data Index: 179400 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1665. Min Range: -4.1665
Max Act: 3.9789. Min Act: -0.1700
Data Index: 152355 (C4 (Web Text))
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1665. Min Range: -4.1665
Max Act: 3.9477. Min Act: -0.1700
Data Index: 1323039 (C4 (Web Text))
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1665. Min Range: -4.1665
Max Act: 3.9477. Min Act: -0.1700
Data Index: 1041428 (C4 (Web Text))
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1665. Min Range: -4.1665
Max Act: 3.9164. Min Act: -0.1700
Data Index: 287891 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1665. Min Range: -4.1665
Max Act: 3.9789. Min Act: -0.1700
Data Index: 622042 (C4 (Web Text))
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1665. Min Range: -4.1665
Max Act: 3.9477. Min Act: -0.1700
Data Index: 772381 (C4 (Web Text))
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1665. Min Range: -4.1665
Max Act: 3.9164. Min Act: -0.1700
Data Index: 783153 (C4 (Web Text))
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19