Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3252 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.1837. Min Range: -2.1837
Max Act: 2.1837. Min Act: -0.1664
Data Index: 8165185 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1837. Min Range: -2.1837
Max Act: 2.1504. Min Act: -0.1695
Data Index: 2861172 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1837. Min Range: -2.1837
Max Act: 2.0499. Min Act: -0.1700
Data Index: 5805706 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1837. Min Range: -2.1837
Max Act: 2.0499. Min Act: -0.1686
Data Index: 5234533 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1837. Min Range: -2.1837
Max Act: 2.0499. Min Act: -0.1654
Data Index: 1805893 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1837. Min Range: -2.1837
Max Act: 2.0499. Min Act: -0.1697
Data Index: 274418 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1837. Min Range: -2.1837
Max Act: 1.9993. Min Act: -0.1700
Data Index: 4713460 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1837. Min Range: -2.1837
Max Act: 1.9993. Min Act: -0.1693
Data Index: 8203874 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1837. Min Range: -2.1837
Max Act: 1.9824. Min Act: -0.1700
Data Index: 7307222 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1837. Min Range: -2.1837
Max Act: 1.9824. Min Act: -0.1689
Data Index: 3181878 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1837. Min Range: -2.1837
Max Act: 1.9655. Min Act: -0.1700
Data Index: 2206525 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1837. Min Range: -2.1837
Max Act: 1.9485. Min Act: -0.1697
Data Index: 7651748 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1837. Min Range: -2.1837
Max Act: 1.9655. Min Act: -0.1693
Data Index: 5326709 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1837. Min Range: -2.1837
Max Act: 1.9485. Min Act: -0.1691
Data Index: 3835060 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1837. Min Range: -2.1837
Max Act: 1.9315. Min Act: -0.1700
Data Index: 3395537 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1837. Min Range: -2.1837
Max Act: 1.9315. Min Act: -0.1683
Data Index: 1255782 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1837. Min Range: -2.1837
Max Act: 1.9315. Min Act: -0.1700
Data Index: 5974519 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1837. Min Range: -2.1837
Max Act: 1.9315. Min Act: -0.1700
Data Index: 5442977 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1837. Min Range: -2.1837
Max Act: 1.9315. Min Act: -0.1699
Data Index: 6385625 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1837. Min Range: -2.1837
Max Act: 1.9315. Min Act: -0.1698
Data Index: 552321 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19