Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 627 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.7923. Min Act: -0.1700
Data Index: 2242909 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.7611. Min Act: -0.1700
Data Index: 44900 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.7298. Min Act: -0.1700
Data Index: 2451147 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.6986. Min Act: -0.1700
Data Index: 5490450 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.6986. Min Act: -0.1699
Data Index: 7399215 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.6673. Min Act: -0.1700
Data Index: 1450570 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.6673. Min Act: -0.1700
Data Index: 4245068 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.6673. Min Act: -0.1700
Data Index: 4707753 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.6673. Min Act: -0.1700
Data Index: 7153900 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.6673. Min Act: -0.1700
Data Index: 4290754 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.6673. Min Act: -0.1700
Data Index: 6925511 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.6673. Min Act: -0.1700
Data Index: 462152 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.6673. Min Act: -0.1700
Data Index: 5107934 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.6361. Min Act: -0.1700
Data Index: 1817392 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.6361. Min Act: -0.1700
Data Index: 3260040 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.6361. Min Act: -0.1700
Data Index: 2242914 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.6361. Min Act: -0.1700
Data Index: 4695688 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.6361. Min Act: -0.1700
Data Index: 1301181 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.6361. Min Act: -0.1700
Data Index: 2952670 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.6048. Min Act: -0.1700
Data Index: 4723821 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19