Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3250 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9984. Min Range: -6.9984
Max Act: 6.9984. Min Act: -0.1700
Data Index: 1483275 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9984. Min Range: -6.9984
Max Act: 6.9671. Min Act: -0.1700
Data Index: 1906202 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9984. Min Range: -6.9984
Max Act: 6.9046. Min Act: -0.1700
Data Index: 5637932 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9984. Min Range: -6.9984
Max Act: 6.9359. Min Act: -0.1700
Data Index: 5124755 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9984. Min Range: -6.9984
Max Act: 6.9046. Min Act: -0.1700
Data Index: 4753193 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9984. Min Range: -6.9984
Max Act: 6.8734. Min Act: -0.1700
Data Index: 6612062 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9984. Min Range: -6.9984
Max Act: 6.8421. Min Act: -0.1700
Data Index: 1003768 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9984. Min Range: -6.9984
Max Act: 6.8109. Min Act: -0.1700
Data Index: 7684109 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9984. Min Range: -6.9984
Max Act: 6.8109. Min Act: -0.1700
Data Index: 2759641 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9984. Min Range: -6.9984
Max Act: 6.7484. Min Act: -0.1700
Data Index: 238558 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9984. Min Range: -6.9984
Max Act: 6.6859. Min Act: -0.1700
Data Index: 6469486 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9984. Min Range: -6.9984
Max Act: 6.7171. Min Act: -0.1700
Data Index: 2902531 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9984. Min Range: -6.9984
Max Act: 6.7171. Min Act: -0.1700
Data Index: 5380237 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9984. Min Range: -6.9984
Max Act: 6.6859. Min Act: -0.1700
Data Index: 3107846 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9984. Min Range: -6.9984
Max Act: 6.6546. Min Act: -0.1700
Data Index: 5481109 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9984. Min Range: -6.9984
Max Act: 6.6546. Min Act: -0.1700
Data Index: 2426005 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9984. Min Range: -6.9984
Max Act: 6.6234. Min Act: -0.1700
Data Index: 7063117 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9984. Min Range: -6.9984
Max Act: 6.6234. Min Act: -0.1700
Data Index: 6387674 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9984. Min Range: -6.9984
Max Act: 6.6234. Min Act: -0.1700
Data Index: 6890134 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9984. Min Range: -6.9984
Max Act: 6.6234. Min Act: -0.1700
Data Index: 3389526 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19