Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2492 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6032. Min Range: -7.6032
Max Act: 7.6032. Min Act: -0.1700
Data Index: 1893098 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6032. Min Range: -7.6032
Max Act: 6.4157. Min Act: -0.1700
Data Index: 3407734 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6032. Min Range: -7.6032
Max Act: 6.3220. Min Act: -0.1700
Data Index: 8597259 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6032. Min Range: -7.6032
Max Act: 6.3220. Min Act: -0.1700
Data Index: 11951 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6032. Min Range: -7.6032
Max Act: 6.2907. Min Act: -0.1700
Data Index: 246181 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6032. Min Range: -7.6032
Max Act: 6.3220. Min Act: -0.1700
Data Index: 6418177 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6032. Min Range: -7.6032
Max Act: 6.2595. Min Act: -0.1700
Data Index: 8201840 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6032. Min Range: -7.6032
Max Act: 6.2595. Min Act: -0.1700
Data Index: 7889645 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6032. Min Range: -7.6032
Max Act: 6.2282. Min Act: -0.1700
Data Index: 3230915 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6032. Min Range: -7.6032
Max Act: 6.2282. Min Act: -0.1700
Data Index: 6306220 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6032. Min Range: -7.6032
Max Act: 6.1970. Min Act: -0.1700
Data Index: 531114 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6032. Min Range: -7.6032
Max Act: 6.1657. Min Act: -0.1700
Data Index: 1930210 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6032. Min Range: -7.6032
Max Act: 6.1970. Min Act: -0.1700
Data Index: 6089215 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6032. Min Range: -7.6032
Max Act: 6.1345. Min Act: -0.1700
Data Index: 5680368 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6032. Min Range: -7.6032
Max Act: 6.1345. Min Act: -0.1700
Data Index: 5648739 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6032. Min Range: -7.6032
Max Act: 6.1032. Min Act: -0.1700
Data Index: 4710578 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6032. Min Range: -7.6032
Max Act: 6.1345. Min Act: -0.1700
Data Index: 2071355 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6032. Min Range: -7.6032
Max Act: 6.0720. Min Act: -0.1700
Data Index: 8414339 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6032. Min Range: -7.6032
Max Act: 6.0720. Min Act: -0.1700
Data Index: 7289042 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6032. Min Range: -7.6032
Max Act: 6.0407. Min Act: -0.1700
Data Index: 7109632 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19