Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1918 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1933. Min Range: -4.1933
Max Act: 4.1620. Min Act: -0.1700
Data Index: 2851070 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1933. Min Range: -4.1933
Max Act: 4.1933. Min Act: -0.1700
Data Index: 2301775 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1933. Min Range: -4.1933
Max Act: 4.0995. Min Act: -0.1700
Data Index: 2851068 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1933. Min Range: -4.1933
Max Act: 4.0370. Min Act: -0.1700
Data Index: 7931498 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1933. Min Range: -4.1933
Max Act: 4.0682. Min Act: -0.1700
Data Index: 5348555 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1933. Min Range: -4.1933
Max Act: 4.0370. Min Act: -0.1700
Data Index: 1835296 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1933. Min Range: -4.1933
Max Act: 4.0057. Min Act: -0.1700
Data Index: 1519993 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1933. Min Range: -4.1933
Max Act: 4.0057. Min Act: -0.1700
Data Index: 5461420 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1933. Min Range: -4.1933
Max Act: 4.0057. Min Act: -0.1700
Data Index: 1105663 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1933. Min Range: -4.1933
Max Act: 4.0057. Min Act: -0.1700
Data Index: 6616107 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1933. Min Range: -4.1933
Max Act: 3.9745. Min Act: -0.1700
Data Index: 5091802 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1933. Min Range: -4.1933
Max Act: 3.9745. Min Act: -0.1700
Data Index: 4767362 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1933. Min Range: -4.1933
Max Act: 3.9745. Min Act: -0.1700
Data Index: 6704683 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1933. Min Range: -4.1933
Max Act: 3.9745. Min Act: -0.1700
Data Index: 423179 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1933. Min Range: -4.1933
Max Act: 3.9745. Min Act: -0.1700
Data Index: 7977485 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1933. Min Range: -4.1933
Max Act: 3.9432. Min Act: -0.1700
Data Index: 745538 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1933. Min Range: -4.1933
Max Act: 3.9432. Min Act: -0.1700
Data Index: 5606698 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1933. Min Range: -4.1933
Max Act: 3.9119. Min Act: -0.1700
Data Index: 1185774 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1933. Min Range: -4.1933
Max Act: 3.8807. Min Act: -0.1700
Data Index: 3437582 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1933. Min Range: -4.1933
Max Act: 3.8650. Min Act: -0.1700
Data Index: 2995615 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #19