Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2865 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9750. Min Range: -3.9750
Max Act: 3.9750. Min Act: -0.1700
Data Index: 2164029 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9750. Min Range: -3.9750
Max Act: 3.9437. Min Act: -0.1700
Data Index: 2164028 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9750. Min Range: -3.9750
Max Act: 3.9124. Min Act: -0.1700
Data Index: 6174786 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9750. Min Range: -3.9750
Max Act: 3.8812. Min Act: -0.1700
Data Index: 4398636 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9750. Min Range: -3.9750
Max Act: 3.8968. Min Act: -0.1700
Data Index: 6814955 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9750. Min Range: -3.9750
Max Act: 3.8655. Min Act: -0.1700
Data Index: 7862142 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9750. Min Range: -3.9750
Max Act: 3.8499. Min Act: -0.1700
Data Index: 5307026 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9750. Min Range: -3.9750
Max Act: 3.8343. Min Act: -0.1700
Data Index: 8816683 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9750. Min Range: -3.9750
Max Act: 3.8499. Min Act: -0.1700
Data Index: 2164027 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9750. Min Range: -3.9750
Max Act: 3.8499. Min Act: -0.1700
Data Index: 1751903 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9750. Min Range: -3.9750
Max Act: 3.8186. Min Act: -0.1700
Data Index: 4328168 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9750. Min Range: -3.9750
Max Act: 3.8343. Min Act: -0.1700
Data Index: 5307027 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9750. Min Range: -3.9750
Max Act: 3.8343. Min Act: -0.1700
Data Index: 5441160 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9750. Min Range: -3.9750
Max Act: 3.8030. Min Act: -0.1700
Data Index: 7928076 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9750. Min Range: -3.9750
Max Act: 3.8030. Min Act: -0.1700
Data Index: 6393791 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9750. Min Range: -3.9750
Max Act: 3.7874. Min Act: -0.1700
Data Index: 2569746 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9750. Min Range: -3.9750
Max Act: 3.8186. Min Act: -0.1700
Data Index: 4999026 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9750. Min Range: -3.9750
Max Act: 3.8030. Min Act: -0.1700
Data Index: 5831048 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9750. Min Range: -3.9750
Max Act: 3.8186. Min Act: -0.1700
Data Index: 21697 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9750. Min Range: -3.9750
Max Act: 3.8030. Min Act: -0.1700
Data Index: 7134720 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #19