Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3575 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.9717. Min Range: -12.9717
Max Act: 12.9717. Min Act: -0.1700
Data Index: 1771786 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.9717. Min Range: -12.9717
Max Act: 12.5342. Min Act: -0.1700
Data Index: 1143685 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.9717. Min Range: -12.9717
Max Act: 12.4717. Min Act: -0.1700
Data Index: 408096 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.9717. Min Range: -12.9717
Max Act: 12.0967. Min Act: -0.1700
Data Index: 3576769 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.9717. Min Range: -12.9717
Max Act: 12.0342. Min Act: -0.1700
Data Index: 3771949 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.9717. Min Range: -12.9717
Max Act: 11.9717. Min Act: -0.1700
Data Index: 3681947 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.9717. Min Range: -12.9717
Max Act: 11.9092. Min Act: -0.1700
Data Index: 6008056 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.9717. Min Range: -12.9717
Max Act: 11.8467. Min Act: -0.1700
Data Index: 4075327 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.9717. Min Range: -12.9717
Max Act: 11.7842. Min Act: -0.1700
Data Index: 408098 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.9717. Min Range: -12.9717
Max Act: 11.7217. Min Act: -0.1700
Data Index: 8502421 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.9717. Min Range: -12.9717
Max Act: 11.7842. Min Act: -0.1700
Data Index: 2052314 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.9717. Min Range: -12.9717
Max Act: 11.5967. Min Act: -0.1700
Data Index: 923604 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.9717. Min Range: -12.9717
Max Act: 11.5967. Min Act: -0.1700
Data Index: 8282771 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.9717. Min Range: -12.9717
Max Act: 11.5342. Min Act: -0.1700
Data Index: 6738719 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.9717. Min Range: -12.9717
Max Act: 11.5342. Min Act: -0.1700
Data Index: 3012637 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.9717. Min Range: -12.9717
Max Act: 11.4717. Min Act: -0.1700
Data Index: 1439912 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.9717. Min Range: -12.9717
Max Act: 11.4717. Min Act: -0.1700
Data Index: 3057838 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.9717. Min Range: -12.9717
Max Act: 11.4717. Min Act: -0.1700
Data Index: 3327876 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.9717. Min Range: -12.9717
Max Act: 11.3467. Min Act: -0.1700
Data Index: 4286650 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.9717. Min Range: -12.9717
Max Act: 11.3467. Min Act: -0.1700
Data Index: 6837273 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #19