Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2546 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8210. Min Range: -7.8210
Max Act: 7.8210. Min Act: -0.1700
Data Index: 7408352 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8210. Min Range: -7.8210
Max Act: 7.6023. Min Act: -0.1700
Data Index: 585643 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8210. Min Range: -7.8210
Max Act: 7.2585. Min Act: -0.1700
Data Index: 7566498 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8210. Min Range: -7.8210
Max Act: 7.1648. Min Act: -0.1700
Data Index: 1578773 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8210. Min Range: -7.8210
Max Act: 7.1023. Min Act: -0.1700
Data Index: 3068923 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8210. Min Range: -7.8210
Max Act: 7.1023. Min Act: -0.1700
Data Index: 5387941 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8210. Min Range: -7.8210
Max Act: 7.0710. Min Act: -0.1700
Data Index: 4025476 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8210. Min Range: -7.8210
Max Act: 7.0398. Min Act: -0.1700
Data Index: 3818780 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8210. Min Range: -7.8210
Max Act: 7.0710. Min Act: -0.1700
Data Index: 986566 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8210. Min Range: -7.8210
Max Act: 7.0085. Min Act: -0.1700
Data Index: 5820115 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8210. Min Range: -7.8210
Max Act: 6.9773. Min Act: -0.1700
Data Index: 6489234 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8210. Min Range: -7.8210
Max Act: 6.9148. Min Act: -0.1700
Data Index: 1398088 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8210. Min Range: -7.8210
Max Act: 6.9460. Min Act: -0.1700
Data Index: 8254084 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8210. Min Range: -7.8210
Max Act: 6.9460. Min Act: -0.1700
Data Index: 7477530 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8210. Min Range: -7.8210
Max Act: 6.9148. Min Act: -0.1700
Data Index: 3068924 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8210. Min Range: -7.8210
Max Act: 6.9148. Min Act: -0.1700
Data Index: 50775 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8210. Min Range: -7.8210
Max Act: 6.8835. Min Act: -0.1700
Data Index: 412291 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8210. Min Range: -7.8210
Max Act: 6.8523. Min Act: -0.1700
Data Index: 8300964 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8210. Min Range: -7.8210
Max Act: 6.8210. Min Act: -0.1700
Data Index: 7926843 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8210. Min Range: -7.8210
Max Act: 6.8210. Min Act: -0.1700
Data Index: 6624185 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #19