Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 728 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5885. Min Range: -9.5885
Max Act: 9.5885. Min Act: -0.1700
Data Index: 5560837 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5885. Min Range: -9.5885
Max Act: 9.2135. Min Act: -0.1700
Data Index: 1754379 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5885. Min Range: -9.5885
Max Act: 9.2135. Min Act: -0.1700
Data Index: 4117124 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5885. Min Range: -9.5885
Max Act: 8.9010. Min Act: -0.1700
Data Index: 8584177 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5885. Min Range: -9.5885
Max Act: 8.8385. Min Act: -0.1700
Data Index: 1476081 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5885. Min Range: -9.5885
Max Act: 8.7760. Min Act: -0.1700
Data Index: 4227351 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5885. Min Range: -9.5885
Max Act: 8.7760. Min Act: -0.1700
Data Index: 5336839 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5885. Min Range: -9.5885
Max Act: 8.7760. Min Act: -0.1700
Data Index: 5380191 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5885. Min Range: -9.5885
Max Act: 8.7135. Min Act: -0.1700
Data Index: 3361820 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5885. Min Range: -9.5885
Max Act: 8.7135. Min Act: -0.1700
Data Index: 6899464 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5885. Min Range: -9.5885
Max Act: 8.7760. Min Act: -0.1700
Data Index: 2873044 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5885. Min Range: -9.5885
Max Act: 8.6510. Min Act: -0.1700
Data Index: 2652912 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5885. Min Range: -9.5885
Max Act: 8.7760. Min Act: -0.1700
Data Index: 1809833 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5885. Min Range: -9.5885
Max Act: 8.6510. Min Act: -0.1700
Data Index: 6296540 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5885. Min Range: -9.5885
Max Act: 8.6510. Min Act: -0.1700
Data Index: 1892545 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5885. Min Range: -9.5885
Max Act: 8.6510. Min Act: -0.1700
Data Index: 5945186 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5885. Min Range: -9.5885
Max Act: 8.6510. Min Act: -0.1700
Data Index: 5854764 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5885. Min Range: -9.5885
Max Act: 8.5885. Min Act: -0.1700
Data Index: 8023799 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5885. Min Range: -9.5885
Max Act: 8.5885. Min Act: -0.1700
Data Index: 302426 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5885. Min Range: -9.5885
Max Act: 8.5260. Min Act: -0.1700
Data Index: 4126237 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #19