Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5374 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3548. Min Range: -7.3548
Max Act: 7.3548. Min Act: -0.1700
Data Index: 5807146 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3548. Min Range: -7.3548
Max Act: 6.9486. Min Act: -0.1700
Data Index: 8541942 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3548. Min Range: -7.3548
Max Act: 6.9173. Min Act: -0.1700
Data Index: 7575217 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3548. Min Range: -7.3548
Max Act: 6.8548. Min Act: -0.1700
Data Index: 1366375 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3548. Min Range: -7.3548
Max Act: 6.7923. Min Act: -0.1700
Data Index: 5419420 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3548. Min Range: -7.3548
Max Act: 6.7923. Min Act: -0.1700
Data Index: 3890410 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3548. Min Range: -7.3548
Max Act: 6.7923. Min Act: -0.1700
Data Index: 6695502 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3548. Min Range: -7.3548
Max Act: 6.7923. Min Act: -0.1700
Data Index: 411188 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3548. Min Range: -7.3548
Max Act: 6.7298. Min Act: -0.1700
Data Index: 4858885 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3548. Min Range: -7.3548
Max Act: 6.6986. Min Act: -0.1700
Data Index: 3627581 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3548. Min Range: -7.3548
Max Act: 6.6986. Min Act: -0.1700
Data Index: 5062807 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3548. Min Range: -7.3548
Max Act: 6.6986. Min Act: -0.1700
Data Index: 4974747 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3548. Min Range: -7.3548
Max Act: 6.6673. Min Act: -0.1700
Data Index: 5612544 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3548. Min Range: -7.3548
Max Act: 6.6048. Min Act: -0.1700
Data Index: 8444015 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3548. Min Range: -7.3548
Max Act: 6.5736. Min Act: -0.1700
Data Index: 3510193 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3548. Min Range: -7.3548
Max Act: 6.6361. Min Act: -0.1700
Data Index: 1403277 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3548. Min Range: -7.3548
Max Act: 6.6048. Min Act: -0.1700
Data Index: 8558693 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3548. Min Range: -7.3548
Max Act: 6.5423. Min Act: -0.1700
Data Index: 8284838 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3548. Min Range: -7.3548
Max Act: 6.5423. Min Act: -0.1700
Data Index: 7315809 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3548. Min Range: -7.3548
Max Act: 6.5423. Min Act: -0.1700
Data Index: 168130 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #19