Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2726 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8070. Min Range: -2.8070
Max Act: 2.8070. Min Act: -0.1700
Data Index: 8532922 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8070. Min Range: -2.8070
Max Act: 2.7910. Min Act: -0.1700
Data Index: 5698867 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8070. Min Range: -2.8070
Max Act: 2.7751. Min Act: -0.1700
Data Index: 2385418 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8070. Min Range: -2.8070
Max Act: 2.7751. Min Act: -0.1700
Data Index: 3016716 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8070. Min Range: -2.8070
Max Act: 2.7432. Min Act: -0.1700
Data Index: 5097774 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8070. Min Range: -2.8070
Max Act: 2.7272. Min Act: -0.1700
Data Index: 157273 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8070. Min Range: -2.8070
Max Act: 2.7272. Min Act: -0.1700
Data Index: 2898633 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8070. Min Range: -2.8070
Max Act: 2.7272. Min Act: -0.1700
Data Index: 1602647 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8070. Min Range: -2.8070
Max Act: 2.7272. Min Act: -0.1700
Data Index: 3329329 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8070. Min Range: -2.8070
Max Act: 2.6952. Min Act: -0.1700
Data Index: 7533246 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8070. Min Range: -2.8070
Max Act: 2.7112. Min Act: -0.1700
Data Index: 5463997 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8070. Min Range: -2.8070
Max Act: 2.6792. Min Act: -0.1700
Data Index: 4419838 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8070. Min Range: -2.8070
Max Act: 2.6471. Min Act: -0.1700
Data Index: 4523574 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8070. Min Range: -2.8070
Max Act: 2.6792. Min Act: -0.1700
Data Index: 7519799 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8070. Min Range: -2.8070
Max Act: 2.6632. Min Act: -0.1700
Data Index: 8011752 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8070. Min Range: -2.8070
Max Act: 2.6632. Min Act: -0.1700
Data Index: 4163143 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8070. Min Range: -2.8070
Max Act: 2.6632. Min Act: -0.1700
Data Index: 7411964 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8070. Min Range: -2.8070
Max Act: 2.6311. Min Act: -0.1700
Data Index: 4180646 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8070. Min Range: -2.8070
Max Act: 2.6311. Min Act: -0.1700
Data Index: 1128322 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8070. Min Range: -2.8070
Max Act: 2.6311. Min Act: -0.1700
Data Index: 8394090 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19