Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5532 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.4293. Min Range: -10.4293
Max Act: 10.4293. Min Act: -0.1700
Data Index: 2172597 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4293. Min Range: -10.4293
Max Act: 10.4293. Min Act: -0.1700
Data Index: 3641059 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4293. Min Range: -10.4293
Max Act: 10.1168. Min Act: -0.1700
Data Index: 6126873 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4293. Min Range: -10.4293
Max Act: 10.0543. Min Act: -0.1700
Data Index: 7878514 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4293. Min Range: -10.4293
Max Act: 10.0543. Min Act: -0.1700
Data Index: 6205167 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4293. Min Range: -10.4293
Max Act: 10.0543. Min Act: -0.1700
Data Index: 1403066 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4293. Min Range: -10.4293
Max Act: 9.8668. Min Act: -0.1700
Data Index: 6833982 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4293. Min Range: -10.4293
Max Act: 9.8668. Min Act: -0.1700
Data Index: 4867359 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4293. Min Range: -10.4293
Max Act: 9.8043. Min Act: -0.1700
Data Index: 3887856 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4293. Min Range: -10.4293
Max Act: 9.8043. Min Act: -0.1700
Data Index: 6447312 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4293. Min Range: -10.4293
Max Act: 9.6793. Min Act: -0.1700
Data Index: 1079688 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4293. Min Range: -10.4293
Max Act: 9.6793. Min Act: -0.1700
Data Index: 7024533 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4293. Min Range: -10.4293
Max Act: 9.6793. Min Act: -0.1700
Data Index: 1224463 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4293. Min Range: -10.4293
Max Act: 9.6793. Min Act: -0.1700
Data Index: 8196653 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4293. Min Range: -10.4293
Max Act: 9.6793. Min Act: -0.1700
Data Index: 2319843 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4293. Min Range: -10.4293
Max Act: 9.6793. Min Act: -0.1700
Data Index: 5920010 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4293. Min Range: -10.4293
Max Act: 9.6168. Min Act: -0.1700
Data Index: 1303912 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4293. Min Range: -10.4293
Max Act: 9.5543. Min Act: -0.1700
Data Index: 3871104 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4293. Min Range: -10.4293
Max Act: 9.5543. Min Act: -0.1700
Data Index: 5433202 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4293. Min Range: -10.4293
Max Act: 9.5543. Min Act: -0.1700
Data Index: 5652472 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19