Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4911 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7984. Min Range: -6.7984
Max Act: 6.7984. Min Act: -0.1700
Data Index: 2155589 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7984. Min Range: -6.7984
Max Act: 6.5796. Min Act: -0.1700
Data Index: 499956 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7984. Min Range: -6.7984
Max Act: 6.5484. Min Act: -0.1700
Data Index: 4536764 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7984. Min Range: -6.7984
Max Act: 6.3609. Min Act: -0.1700
Data Index: 7312104 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7984. Min Range: -6.7984
Max Act: 6.2671. Min Act: -0.1700
Data Index: 5313902 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7984. Min Range: -6.7984
Max Act: 6.1734. Min Act: -0.1700
Data Index: 5515987 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7984. Min Range: -6.7984
Max Act: 6.1734. Min Act: -0.1700
Data Index: 2369284 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7984. Min Range: -6.7984
Max Act: 6.1109. Min Act: -0.1700
Data Index: 8490525 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7984. Min Range: -6.7984
Max Act: 6.0796. Min Act: -0.1700
Data Index: 6965068 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7984. Min Range: -6.7984
Max Act: 6.1109. Min Act: -0.1700
Data Index: 6570752 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7984. Min Range: -6.7984
Max Act: 6.0796. Min Act: -0.1700
Data Index: 6306765 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7984. Min Range: -6.7984
Max Act: 6.0796. Min Act: -0.1700
Data Index: 304958 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7984. Min Range: -6.7984
Max Act: 6.0796. Min Act: -0.1700
Data Index: 8357945 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7984. Min Range: -6.7984
Max Act: 6.0796. Min Act: -0.1700
Data Index: 6173626 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7984. Min Range: -6.7984
Max Act: 6.0796. Min Act: -0.1700
Data Index: 2890741 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7984. Min Range: -6.7984
Max Act: 6.0171. Min Act: -0.1700
Data Index: 338787 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7984. Min Range: -6.7984
Max Act: 6.0484. Min Act: -0.1700
Data Index: 8550108 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7984. Min Range: -6.7984
Max Act: 6.0171. Min Act: -0.1700
Data Index: 253441 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7984. Min Range: -6.7984
Max Act: 6.0171. Min Act: -0.1700
Data Index: 4430575 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7984. Min Range: -6.7984
Max Act: 6.0171. Min Act: -0.1700
Data Index: 4323633 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19