Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3314 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7699. Min Range: -6.7699
Max Act: 6.7699. Min Act: -0.1700
Data Index: 8584793 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7699. Min Range: -6.7699
Max Act: 6.7387. Min Act: -0.1700
Data Index: 3331289 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7699. Min Range: -6.7699
Max Act: 6.7074. Min Act: -0.1700
Data Index: 1055331 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7699. Min Range: -6.7699
Max Act: 6.6762. Min Act: -0.1700
Data Index: 6615272 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7699. Min Range: -6.7699
Max Act: 6.6449. Min Act: -0.1700
Data Index: 101675 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7699. Min Range: -6.7699
Max Act: 6.6137. Min Act: -0.1700
Data Index: 414684 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7699. Min Range: -6.7699
Max Act: 6.5824. Min Act: -0.1700
Data Index: 6866793 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7699. Min Range: -6.7699
Max Act: 6.5824. Min Act: -0.1700
Data Index: 6866282 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7699. Min Range: -6.7699
Max Act: 6.5512. Min Act: -0.1700
Data Index: 7023462 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7699. Min Range: -6.7699
Max Act: 6.5512. Min Act: -0.1700
Data Index: 3630815 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7699. Min Range: -6.7699
Max Act: 6.5199. Min Act: -0.1700
Data Index: 7548851 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7699. Min Range: -6.7699
Max Act: 6.5199. Min Act: -0.1700
Data Index: 1434068 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7699. Min Range: -6.7699
Max Act: 6.5199. Min Act: -0.1700
Data Index: 7949897 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7699. Min Range: -6.7699
Max Act: 6.4887. Min Act: -0.1700
Data Index: 598440 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7699. Min Range: -6.7699
Max Act: 6.4887. Min Act: -0.1700
Data Index: 1841661 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7699. Min Range: -6.7699
Max Act: 6.4574. Min Act: -0.1700
Data Index: 2767547 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7699. Min Range: -6.7699
Max Act: 6.4574. Min Act: -0.1700
Data Index: 576317 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7699. Min Range: -6.7699
Max Act: 6.4262. Min Act: -0.1700
Data Index: 7070254 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7699. Min Range: -6.7699
Max Act: 6.4262. Min Act: -0.1700
Data Index: 6238004 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7699. Min Range: -6.7699
Max Act: 6.4262. Min Act: -0.1700
Data Index: 3339300 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #19