Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 50 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2938. Min Range: -5.2938
Max Act: 5.2938. Min Act: -0.1700
Data Index: 994762 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2938. Min Range: -5.2938
Max Act: 5.2001. Min Act: -0.1700
Data Index: 1475468 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2938. Min Range: -5.2938
Max Act: 5.2001. Min Act: -0.1700
Data Index: 506938 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2938. Min Range: -5.2938
Max Act: 5.1688. Min Act: -0.1700
Data Index: 5289804 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2938. Min Range: -5.2938
Max Act: 5.1688. Min Act: -0.1700
Data Index: 4684695 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2938. Min Range: -5.2938
Max Act: 5.1376. Min Act: -0.1700
Data Index: 2276527 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2938. Min Range: -5.2938
Max Act: 5.1688. Min Act: -0.1700
Data Index: 7008147 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2938. Min Range: -5.2938
Max Act: 5.1376. Min Act: -0.1700
Data Index: 320158 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2938. Min Range: -5.2938
Max Act: 5.1376. Min Act: -0.1700
Data Index: 815640 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2938. Min Range: -5.2938
Max Act: 5.1063. Min Act: -0.1700
Data Index: 360222 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2938. Min Range: -5.2938
Max Act: 5.1063. Min Act: -0.1700
Data Index: 6002139 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2938. Min Range: -5.2938
Max Act: 5.1063. Min Act: -0.1700
Data Index: 4549612 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2938. Min Range: -5.2938
Max Act: 5.0751. Min Act: -0.1700
Data Index: 883535 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2938. Min Range: -5.2938
Max Act: 5.0438. Min Act: -0.1700
Data Index: 973045 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2938. Min Range: -5.2938
Max Act: 4.9813. Min Act: -0.1700
Data Index: 6691953 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2938. Min Range: -5.2938
Max Act: 5.0126. Min Act: -0.1700
Data Index: 6663606 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2938. Min Range: -5.2938
Max Act: 4.9813. Min Act: -0.1700
Data Index: 6663601 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2938. Min Range: -5.2938
Max Act: 4.9813. Min Act: -0.1700
Data Index: 3978775 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2938. Min Range: -5.2938
Max Act: 4.9813. Min Act: -0.1700
Data Index: 4978174 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2938. Min Range: -5.2938
Max Act: 4.9813. Min Act: -0.1700
Data Index: 6663586 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #19