Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2028 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 0.7798. Min Range: -0.7798
Max Act: 0.7798. Min Act: -0.1700
Data Index: 4185808 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7798. Min Range: -0.7798
Max Act: 0.7798. Min Act: -0.1700
Data Index: 2459155 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7798. Min Range: -0.7798
Max Act: 0.7798. Min Act: -0.1700
Data Index: 187791 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7798. Min Range: -0.7798
Max Act: 0.7632. Min Act: -0.1700
Data Index: 266345 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7798. Min Range: -0.7798
Max Act: 0.7798. Min Act: -0.1700
Data Index: 2454100 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7798. Min Range: -0.7798
Max Act: 0.7798. Min Act: -0.1700
Data Index: 4843737 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7798. Min Range: -0.7798
Max Act: 0.7798. Min Act: -0.1700
Data Index: 4624663 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7798. Min Range: -0.7798
Max Act: 0.7798. Min Act: -0.1700
Data Index: 1573881 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7798. Min Range: -0.7798
Max Act: 0.7632. Min Act: -0.1700
Data Index: 2402983 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7798. Min Range: -0.7798
Max Act: 0.7632. Min Act: -0.1700
Data Index: 1311300 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7798. Min Range: -0.7798
Max Act: 0.7798. Min Act: -0.1700
Data Index: 1366506 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7798. Min Range: -0.7798
Max Act: 0.7798. Min Act: -0.1700
Data Index: 2157093 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7798. Min Range: -0.7798
Max Act: 0.7798. Min Act: -0.1700
Data Index: 3801158 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7798. Min Range: -0.7798
Max Act: 0.7798. Min Act: -0.1700
Data Index: 3516495 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7798. Min Range: -0.7798
Max Act: 0.7798. Min Act: -0.1700
Data Index: 1736578 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7798. Min Range: -0.7798
Max Act: 0.7798. Min Act: -0.1700
Data Index: 3134189 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7798. Min Range: -0.7798
Max Act: 0.7632. Min Act: -0.1700
Data Index: 993027 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7798. Min Range: -0.7798
Max Act: 0.7632. Min Act: -0.1700
Data Index: 1464246 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7798. Min Range: -0.7798
Max Act: 0.7798. Min Act: -0.1700
Data Index: 859896 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7798. Min Range: -0.7798
Max Act: 0.7632. Min Act: -0.1700
Data Index: 3043634 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19