Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3710 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1673. Min Range: -8.1673
Max Act: 8.1673. Min Act: -0.1700
Data Index: 5312154 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1673. Min Range: -8.1673
Max Act: 8.0110. Min Act: -0.1700
Data Index: 6500287 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1673. Min Range: -8.1673
Max Act: 7.6673. Min Act: -0.1700
Data Index: 4739356 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1673. Min Range: -8.1673
Max Act: 7.6360. Min Act: -0.1700
Data Index: 3957779 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1673. Min Range: -8.1673
Max Act: 7.6673. Min Act: -0.1700
Data Index: 3957778 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1673. Min Range: -8.1673
Max Act: 7.6048. Min Act: -0.1700
Data Index: 1428815 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1673. Min Range: -8.1673
Max Act: 7.6048. Min Act: -0.1700
Data Index: 1758749 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1673. Min Range: -8.1673
Max Act: 7.5423. Min Act: -0.1700
Data Index: 8207528 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1673. Min Range: -8.1673
Max Act: 7.5735. Min Act: -0.1700
Data Index: 3756257 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1673. Min Range: -8.1673
Max Act: 7.5423. Min Act: -0.1700
Data Index: 4406191 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1673. Min Range: -8.1673
Max Act: 7.5110. Min Act: -0.1700
Data Index: 6855531 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1673. Min Range: -8.1673
Max Act: 7.4173. Min Act: -0.1700
Data Index: 8148873 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1673. Min Range: -8.1673
Max Act: 7.4173. Min Act: -0.1700
Data Index: 1601812 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1673. Min Range: -8.1673
Max Act: 7.4173. Min Act: -0.1700
Data Index: 2007760 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1673. Min Range: -8.1673
Max Act: 7.3860. Min Act: -0.1700
Data Index: 6782887 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1673. Min Range: -8.1673
Max Act: 7.3860. Min Act: -0.1700
Data Index: 4733761 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1673. Min Range: -8.1673
Max Act: 7.3235. Min Act: -0.1700
Data Index: 7547086 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1673. Min Range: -8.1673
Max Act: 7.3235. Min Act: -0.1700
Data Index: 4840673 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1673. Min Range: -8.1673
Max Act: 7.2923. Min Act: -0.1700
Data Index: 1297411 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1673. Min Range: -8.1673
Max Act: 7.2923. Min Act: -0.1700
Data Index: 8012889 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #19