Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3437 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8734. Min Range: -5.8734
Max Act: 5.8734. Min Act: -0.1700
Data Index: 5708533 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8734. Min Range: -5.8734
Max Act: 5.8109. Min Act: -0.1700
Data Index: 8786382 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8734. Min Range: -5.8734
Max Act: 5.7796. Min Act: -0.1700
Data Index: 2679505 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8734. Min Range: -5.8734
Max Act: 5.7171. Min Act: -0.1700
Data Index: 2982662 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8734. Min Range: -5.8734
Max Act: 5.7171. Min Act: -0.1700
Data Index: 4705282 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8734. Min Range: -5.8734
Max Act: 5.6859. Min Act: -0.1700
Data Index: 411079 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8734. Min Range: -5.8734
Max Act: 5.5921. Min Act: -0.1700
Data Index: 5082611 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8734. Min Range: -5.8734
Max Act: 5.5296. Min Act: -0.1700
Data Index: 8090488 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8734. Min Range: -5.8734
Max Act: 5.5296. Min Act: -0.1700
Data Index: 2530461 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8734. Min Range: -5.8734
Max Act: 5.4671. Min Act: -0.1700
Data Index: 2630418 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8734. Min Range: -5.8734
Max Act: 5.4671. Min Act: -0.1700
Data Index: 4276858 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8734. Min Range: -5.8734
Max Act: 5.4671. Min Act: -0.1700
Data Index: 6183120 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8734. Min Range: -5.8734
Max Act: 5.4359. Min Act: -0.1700
Data Index: 1178128 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8734. Min Range: -5.8734
Max Act: 5.4046. Min Act: -0.1700
Data Index: 7562881 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8734. Min Range: -5.8734
Max Act: 5.3734. Min Act: -0.1700
Data Index: 2905937 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8734. Min Range: -5.8734
Max Act: 5.4046. Min Act: -0.1700
Data Index: 402831 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8734. Min Range: -5.8734
Max Act: 5.4046. Min Act: -0.1700
Data Index: 2878262 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8734. Min Range: -5.8734
Max Act: 5.4046. Min Act: -0.1700
Data Index: 927616 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8734. Min Range: -5.8734
Max Act: 5.4046. Min Act: -0.1700
Data Index: 8036713 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8734. Min Range: -5.8734
Max Act: 5.4046. Min Act: -0.1700
Data Index: 1135670 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19