Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3096 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3617. Min Range: -5.3617
Max Act: 5.3617. Min Act: -0.1700
Data Index: 2785002 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3617. Min Range: -5.3617
Max Act: 5.2054. Min Act: -0.1697
Data Index: 1535910 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3617. Min Range: -5.3617
Max Act: 5.1742. Min Act: -0.1700
Data Index: 8447834 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3617. Min Range: -5.3617
Max Act: 5.1742. Min Act: -0.1693
Data Index: 8531158 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3617. Min Range: -5.3617
Max Act: 5.1429. Min Act: -0.1700
Data Index: 7346568 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3617. Min Range: -5.3617
Max Act: 5.1429. Min Act: -0.1700
Data Index: 4310234 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3617. Min Range: -5.3617
Max Act: 5.1429. Min Act: -0.1700
Data Index: 6400551 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3617. Min Range: -5.3617
Max Act: 5.1429. Min Act: -0.1582
Data Index: 6949893 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3617. Min Range: -5.3617
Max Act: 5.1117. Min Act: -0.1697
Data Index: 7895904 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3617. Min Range: -5.3617
Max Act: 5.1117. Min Act: -0.1700
Data Index: 8424276 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3617. Min Range: -5.3617
Max Act: 5.0804. Min Act: -0.1700
Data Index: 1847780 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3617. Min Range: -5.3617
Max Act: 5.0804. Min Act: -0.1700
Data Index: 3663376 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3617. Min Range: -5.3617
Max Act: 5.0804. Min Act: -0.1699
Data Index: 1837807 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3617. Min Range: -5.3617
Max Act: 5.0804. Min Act: -0.1693
Data Index: 7304425 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3617. Min Range: -5.3617
Max Act: 5.0804. Min Act: -0.1700
Data Index: 3566719 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3617. Min Range: -5.3617
Max Act: 5.0804. Min Act: -0.1700
Data Index: 5848708 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3617. Min Range: -5.3617
Max Act: 5.0804. Min Act: -0.1700
Data Index: 5299700 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3617. Min Range: -5.3617
Max Act: 5.0804. Min Act: -0.1700
Data Index: 4867388 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3617. Min Range: -5.3617
Max Act: 5.0804. Min Act: -0.1700
Data Index: 2222763 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3617. Min Range: -5.3617
Max Act: 5.0804. Min Act: -0.1696
Data Index: 1956319 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19