Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3592 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9830. Min Range: -4.9830
Max Act: 4.9830. Min Act: -0.1700
Data Index: 6533800 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9830. Min Range: -4.9830
Max Act: 4.8580. Min Act: -0.1700
Data Index: 1393860 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9830. Min Range: -4.9830
Max Act: 4.8580. Min Act: -0.1700
Data Index: 1500697 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9830. Min Range: -4.9830
Max Act: 4.8580. Min Act: -0.1700
Data Index: 762826 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9830. Min Range: -4.9830
Max Act: 4.7955. Min Act: -0.1700
Data Index: 1924070 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9830. Min Range: -4.9830
Max Act: 4.7955. Min Act: -0.1700
Data Index: 2832079 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9830. Min Range: -4.9830
Max Act: 4.7643. Min Act: -0.1700
Data Index: 4063504 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9830. Min Range: -4.9830
Max Act: 4.7643. Min Act: -0.1700
Data Index: 4746809 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9830. Min Range: -4.9830
Max Act: 4.7643. Min Act: -0.1700
Data Index: 3852804 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9830. Min Range: -4.9830
Max Act: 4.7643. Min Act: -0.1700
Data Index: 7662603 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9830. Min Range: -4.9830
Max Act: 4.7330. Min Act: -0.1700
Data Index: 650394 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9830. Min Range: -4.9830
Max Act: 4.7330. Min Act: -0.1700
Data Index: 1802484 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9830. Min Range: -4.9830
Max Act: 4.7330. Min Act: -0.1700
Data Index: 1797748 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9830. Min Range: -4.9830
Max Act: 4.7330. Min Act: -0.1700
Data Index: 6473385 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9830. Min Range: -4.9830
Max Act: 4.7330. Min Act: -0.1700
Data Index: 6362556 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9830. Min Range: -4.9830
Max Act: 4.7643. Min Act: -0.1700
Data Index: 5769418 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9830. Min Range: -4.9830
Max Act: 4.7330. Min Act: -0.1700
Data Index: 3191737 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9830. Min Range: -4.9830
Max Act: 4.7330. Min Act: -0.1700
Data Index: 5216218 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9830. Min Range: -4.9830
Max Act: 4.7330. Min Act: -0.1700
Data Index: 1976036 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9830. Min Range: -4.9830
Max Act: 4.7330. Min Act: -0.1700
Data Index: 558094 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19