Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1803 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3670. Min Range: -4.3670
Max Act: 4.3670. Min Act: -0.1700
Data Index: 5477987 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3670. Min Range: -4.3670
Max Act: 4.2107. Min Act: -0.1700
Data Index: 5517960 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3670. Min Range: -4.3670
Max Act: 4.2107. Min Act: -0.1700
Data Index: 2877431 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3670. Min Range: -4.3670
Max Act: 4.2107. Min Act: -0.1700
Data Index: 3832981 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3670. Min Range: -4.3670
Max Act: 4.1482. Min Act: -0.1700
Data Index: 334140 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3670. Min Range: -4.3670
Max Act: 4.1482. Min Act: -0.1700
Data Index: 1980955 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3670. Min Range: -4.3670
Max Act: 4.1482. Min Act: -0.1700
Data Index: 1232162 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3670. Min Range: -4.3670
Max Act: 4.1482. Min Act: -0.1700
Data Index: 4720181 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3670. Min Range: -4.3670
Max Act: 4.1482. Min Act: -0.1700
Data Index: 1980936 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3670. Min Range: -4.3670
Max Act: 4.1482. Min Act: -0.1700
Data Index: 4471938 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3670. Min Range: -4.3670
Max Act: 4.1482. Min Act: -0.1700
Data Index: 2727794 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3670. Min Range: -4.3670
Max Act: 4.1482. Min Act: -0.1700
Data Index: 5904746 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3670. Min Range: -4.3670
Max Act: 4.1482. Min Act: -0.1700
Data Index: 1232165 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3670. Min Range: -4.3670
Max Act: 4.1482. Min Act: -0.1700
Data Index: 4405054 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3670. Min Range: -4.3670
Max Act: 4.1482. Min Act: -0.1700
Data Index: 2233755 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3670. Min Range: -4.3670
Max Act: 4.1482. Min Act: -0.1700
Data Index: 2215660 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3670. Min Range: -4.3670
Max Act: 4.1482. Min Act: -0.1700
Data Index: 1893737 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3670. Min Range: -4.3670
Max Act: 4.1482. Min Act: -0.1700
Data Index: 2008077 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3670. Min Range: -4.3670
Max Act: 4.1482. Min Act: -0.1700
Data Index: 1261512 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3670. Min Range: -4.3670
Max Act: 4.1482. Min Act: -0.1700
Data Index: 5347707 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19