Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3632 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5941. Min Range: -4.5941
Max Act: 4.5941. Min Act: -0.1700
Data Index: 1061490 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5941. Min Range: -4.5941
Max Act: 4.5629. Min Act: -0.1700
Data Index: 2838124 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5941. Min Range: -4.5941
Max Act: 4.5316. Min Act: -0.1700
Data Index: 1526919 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5941. Min Range: -4.5941
Max Act: 4.5316. Min Act: -0.1700
Data Index: 3494716 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5941. Min Range: -4.5941
Max Act: 4.5316. Min Act: -0.1700
Data Index: 6223783 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5941. Min Range: -4.5941
Max Act: 4.5316. Min Act: -0.1700
Data Index: 1901091 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5941. Min Range: -4.5941
Max Act: 4.5316. Min Act: -0.1700
Data Index: 3636518 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5941. Min Range: -4.5941
Max Act: 4.5004. Min Act: -0.1700
Data Index: 4284428 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5941. Min Range: -4.5941
Max Act: 4.5004. Min Act: -0.1700
Data Index: 961304 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5941. Min Range: -4.5941
Max Act: 4.5004. Min Act: -0.1700
Data Index: 5829513 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5941. Min Range: -4.5941
Max Act: 4.4379. Min Act: -0.1700
Data Index: 789425 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5941. Min Range: -4.5941
Max Act: 4.4691. Min Act: -0.1700
Data Index: 6284236 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5941. Min Range: -4.5941
Max Act: 4.4691. Min Act: -0.1700
Data Index: 6449178 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5941. Min Range: -4.5941
Max Act: 4.4691. Min Act: -0.1700
Data Index: 6871503 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5941. Min Range: -4.5941
Max Act: 4.4691. Min Act: -0.1700
Data Index: 6944327 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5941. Min Range: -4.5941
Max Act: 4.4691. Min Act: -0.1700
Data Index: 7829911 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5941. Min Range: -4.5941
Max Act: 4.4379. Min Act: -0.1700
Data Index: 3460684 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5941. Min Range: -4.5941
Max Act: 4.4066. Min Act: -0.1700
Data Index: 5844185 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5941. Min Range: -4.5941
Max Act: 4.4379. Min Act: -0.1700
Data Index: 5906331 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5941. Min Range: -4.5941
Max Act: 4.4691. Min Act: -0.1700
Data Index: 948367 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #19