Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3578 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0133. Min Range: -6.0133
Max Act: 6.0133. Min Act: -0.1700
Data Index: 2229752 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0133. Min Range: -6.0133
Max Act: 5.8571. Min Act: -0.1700
Data Index: 8721123 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0133. Min Range: -6.0133
Max Act: 5.8571. Min Act: -0.1700
Data Index: 6228486 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0133. Min Range: -6.0133
Max Act: 5.7946. Min Act: -0.1700
Data Index: 4893673 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0133. Min Range: -6.0133
Max Act: 5.7946. Min Act: -0.1700
Data Index: 1444297 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0133. Min Range: -6.0133
Max Act: 5.7633. Min Act: -0.1700
Data Index: 3588517 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0133. Min Range: -6.0133
Max Act: 5.6071. Min Act: -0.1700
Data Index: 8437291 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0133. Min Range: -6.0133
Max Act: 5.6071. Min Act: -0.1700
Data Index: 3804900 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0133. Min Range: -6.0133
Max Act: 5.5446. Min Act: -0.1700
Data Index: 6534296 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0133. Min Range: -6.0133
Max Act: 5.5133. Min Act: -0.1700
Data Index: 4442616 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0133. Min Range: -6.0133
Max Act: 5.4508. Min Act: -0.1700
Data Index: 6087807 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0133. Min Range: -6.0133
Max Act: 5.4196. Min Act: -0.1700
Data Index: 6288937 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0133. Min Range: -6.0133
Max Act: 5.3883. Min Act: -0.1700
Data Index: 6567090 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0133. Min Range: -6.0133
Max Act: 5.3883. Min Act: -0.1700
Data Index: 8764562 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0133. Min Range: -6.0133
Max Act: 5.3258. Min Act: -0.1700
Data Index: 7022122 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0133. Min Range: -6.0133
Max Act: 5.3258. Min Act: -0.1700
Data Index: 8562837 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0133. Min Range: -6.0133
Max Act: 5.3258. Min Act: -0.1700
Data Index: 5932326 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0133. Min Range: -6.0133
Max Act: 5.2946. Min Act: -0.1700
Data Index: 1861083 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0133. Min Range: -6.0133
Max Act: 5.2946. Min Act: -0.1700
Data Index: 6003786 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0133. Min Range: -6.0133
Max Act: 5.2633. Min Act: -0.1700
Data Index: 7774530 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #19