Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5443 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.8031. Min Range: -1.8031
Max Act: 1.8031. Min Act: -0.1698
Data Index: 2205242 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8031. Min Range: -1.8031
Max Act: 1.7686. Min Act: -0.1700
Data Index: 4626021 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8031. Min Range: -1.8031
Max Act: 1.6299. Min Act: -0.1682
Data Index: 8732704 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8031. Min Range: -1.8031
Max Act: 1.6473. Min Act: -0.1700
Data Index: 1321374 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8031. Min Range: -1.8031
Max Act: 1.6124. Min Act: -0.1696
Data Index: 3885973 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8031. Min Range: -1.8031
Max Act: 1.5600. Min Act: -0.1700
Data Index: 1507374 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8031. Min Range: -1.8031
Max Act: 1.5600. Min Act: -0.1687
Data Index: 4626031 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8031. Min Range: -1.8031
Max Act: 1.5600. Min Act: -0.1697
Data Index: 216827 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8031. Min Range: -1.8031
Max Act: 1.5600. Min Act: -0.1700
Data Index: 5403584 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8031. Min Range: -1.8031
Max Act: 1.5425. Min Act: -0.1700
Data Index: 6107859 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8031. Min Range: -1.8031
Max Act: 1.5425. Min Act: -0.1587
Data Index: 7353273 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8031. Min Range: -1.8031
Max Act: 1.5425. Min Act: -0.1700
Data Index: 4400597 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8031. Min Range: -1.8031
Max Act: 1.5600. Min Act: -0.1700
Data Index: 512705 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8031. Min Range: -1.8031
Max Act: 1.5250. Min Act: -0.1700
Data Index: 4626029 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8031. Min Range: -1.8031
Max Act: 1.5250. Min Act: -0.1638
Data Index: 1210003 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8031. Min Range: -1.8031
Max Act: 1.5074. Min Act: -0.1694
Data Index: 4224055 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8031. Min Range: -1.8031
Max Act: 1.5074. Min Act: -0.1697
Data Index: 8393311 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8031. Min Range: -1.8031
Max Act: 1.5074. Min Act: -0.1678
Data Index: 1343264 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8031. Min Range: -1.8031
Max Act: 1.5074. Min Act: -0.1700
Data Index: 1691028 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8031. Min Range: -1.8031
Max Act: 1.4723. Min Act: -0.1700
Data Index: 7885603 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19