Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5352 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1920. Min Range: -7.1920
Max Act: 7.1920. Min Act: -0.1700
Data Index: 8430866 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1920. Min Range: -7.1920
Max Act: 6.9420. Min Act: -0.1700
Data Index: 8767426 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1920. Min Range: -7.1920
Max Act: 6.9108. Min Act: -0.1700
Data Index: 234426 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1920. Min Range: -7.1920
Max Act: 6.7545. Min Act: -0.1700
Data Index: 7175047 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1920. Min Range: -7.1920
Max Act: 6.7233. Min Act: -0.1700
Data Index: 4874928 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1920. Min Range: -7.1920
Max Act: 6.6608. Min Act: -0.1700
Data Index: 969544 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1920. Min Range: -7.1920
Max Act: 6.6608. Min Act: -0.1700
Data Index: 60086 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1920. Min Range: -7.1920
Max Act: 6.5983. Min Act: -0.1700
Data Index: 5509478 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1920. Min Range: -7.1920
Max Act: 6.5983. Min Act: -0.1700
Data Index: 572298 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1920. Min Range: -7.1920
Max Act: 6.5670. Min Act: -0.1700
Data Index: 4443679 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1920. Min Range: -7.1920
Max Act: 6.5670. Min Act: -0.1700
Data Index: 2952765 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1920. Min Range: -7.1920
Max Act: 6.5670. Min Act: -0.1700
Data Index: 298785 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1920. Min Range: -7.1920
Max Act: 6.5670. Min Act: -0.1700
Data Index: 2583565 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1920. Min Range: -7.1920
Max Act: 6.5358. Min Act: -0.1700
Data Index: 7943891 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1920. Min Range: -7.1920
Max Act: 6.5358. Min Act: -0.1700
Data Index: 8073864 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1920. Min Range: -7.1920
Max Act: 6.5045. Min Act: -0.1700
Data Index: 497131 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1920. Min Range: -7.1920
Max Act: 6.5045. Min Act: -0.1700
Data Index: 1128965 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1920. Min Range: -7.1920
Max Act: 6.5045. Min Act: -0.1700
Data Index: 1170459 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1920. Min Range: -7.1920
Max Act: 6.5045. Min Act: -0.1700
Data Index: 5994810 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1920. Min Range: -7.1920
Max Act: 6.5045. Min Act: -0.1700
Data Index: 4058752 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19