Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1739 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1010. Min Range: -4.1010
Max Act: 4.1010. Min Act: -0.1699
Data Index: 4579681 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1010. Min Range: -4.1010
Max Act: 4.1010. Min Act: -0.1700
Data Index: 2535371 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1010. Min Range: -4.1010
Max Act: 4.1010. Min Act: -0.1700
Data Index: 7031133 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1010. Min Range: -4.1010
Max Act: 4.0697. Min Act: -0.1700
Data Index: 6125038 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1010. Min Range: -4.1010
Max Act: 4.0697. Min Act: -0.1700
Data Index: 7029984 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1010. Min Range: -4.1010
Max Act: 4.0697. Min Act: -0.1700
Data Index: 4839094 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1010. Min Range: -4.1010
Max Act: 4.0697. Min Act: -0.1700
Data Index: 1849567 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1010. Min Range: -4.1010
Max Act: 4.0697. Min Act: -0.1699
Data Index: 5803647 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1010. Min Range: -4.1010
Max Act: 4.0385. Min Act: -0.1700
Data Index: 5045520 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1010. Min Range: -4.1010
Max Act: 4.0072. Min Act: -0.1700
Data Index: 8241402 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1010. Min Range: -4.1010
Max Act: 3.9760. Min Act: -0.1698
Data Index: 5513081 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1010. Min Range: -4.1010
Max Act: 4.0072. Min Act: -0.1700
Data Index: 8117502 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1010. Min Range: -4.1010
Max Act: 4.0072. Min Act: -0.1700
Data Index: 8094825 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1010. Min Range: -4.1010
Max Act: 4.0072. Min Act: -0.1700
Data Index: 5887914 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1010. Min Range: -4.1010
Max Act: 4.0072. Min Act: -0.1700
Data Index: 5599164 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1010. Min Range: -4.1010
Max Act: 4.0072. Min Act: -0.1700
Data Index: 2492753 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1010. Min Range: -4.1010
Max Act: 4.0072. Min Act: -0.1700
Data Index: 5318782 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1010. Min Range: -4.1010
Max Act: 4.0072. Min Act: -0.1699
Data Index: 4945501 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1010. Min Range: -4.1010
Max Act: 4.0385. Min Act: -0.1699
Data Index: 3874459 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1010. Min Range: -4.1010
Max Act: 4.0072. Min Act: -0.1700
Data Index: 2934113 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19