Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3757 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1246. Min Range: -6.1246
Max Act: 6.1246. Min Act: -0.1700
Data Index: 4296442 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1246. Min Range: -6.1246
Max Act: 6.0621. Min Act: -0.1700
Data Index: 796475 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1246. Min Range: -6.1246
Max Act: 5.9371. Min Act: -0.1700
Data Index: 6762543 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1246. Min Range: -6.1246
Max Act: 5.9059. Min Act: -0.1700
Data Index: 172867 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1246. Min Range: -6.1246
Max Act: 5.9059. Min Act: -0.1700
Data Index: 7792867 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1246. Min Range: -6.1246
Max Act: 5.9059. Min Act: -0.1700
Data Index: 2733597 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1246. Min Range: -6.1246
Max Act: 5.8746. Min Act: -0.1700
Data Index: 5354984 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1246. Min Range: -6.1246
Max Act: 5.8746. Min Act: -0.1700
Data Index: 8340959 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1246. Min Range: -6.1246
Max Act: 5.8121. Min Act: -0.1700
Data Index: 7174169 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1246. Min Range: -6.1246
Max Act: 5.8121. Min Act: -0.1700
Data Index: 3727524 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1246. Min Range: -6.1246
Max Act: 5.8121. Min Act: -0.1700
Data Index: 2166763 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1246. Min Range: -6.1246
Max Act: 5.7809. Min Act: -0.1700
Data Index: 6660986 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1246. Min Range: -6.1246
Max Act: 5.8121. Min Act: -0.1700
Data Index: 1353947 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1246. Min Range: -6.1246
Max Act: 5.8121. Min Act: -0.1700
Data Index: 8753712 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1246. Min Range: -6.1246
Max Act: 5.7809. Min Act: -0.1700
Data Index: 2078393 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1246. Min Range: -6.1246
Max Act: 5.7809. Min Act: -0.1700
Data Index: 3950184 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1246. Min Range: -6.1246
Max Act: 5.7809. Min Act: -0.1700
Data Index: 3018637 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1246. Min Range: -6.1246
Max Act: 5.8121. Min Act: -0.1700
Data Index: 4867299 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1246. Min Range: -6.1246
Max Act: 5.7809. Min Act: -0.1700
Data Index: 4244268 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1246. Min Range: -6.1246
Max Act: 5.7496. Min Act: -0.1700
Data Index: 3446476 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #19