Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1616 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5008. Min Range: -5.5008
Max Act: 5.5008. Min Act: -0.1700
Data Index: 2911882 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5008. Min Range: -5.5008
Max Act: 5.5008. Min Act: -0.1700
Data Index: 5668446 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5008. Min Range: -5.5008
Max Act: 5.4696. Min Act: -0.1700
Data Index: 656481 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5008. Min Range: -5.5008
Max Act: 5.4696. Min Act: -0.1700
Data Index: 4280439 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5008. Min Range: -5.5008
Max Act: 5.4383. Min Act: -0.1700
Data Index: 8222670 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5008. Min Range: -5.5008
Max Act: 5.4383. Min Act: -0.1700
Data Index: 1111669 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5008. Min Range: -5.5008
Max Act: 5.4071. Min Act: -0.1700
Data Index: 165150 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5008. Min Range: -5.5008
Max Act: 5.4071. Min Act: -0.1700
Data Index: 7204810 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5008. Min Range: -5.5008
Max Act: 5.3758. Min Act: -0.1700
Data Index: 931 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5008. Min Range: -5.5008
Max Act: 5.3758. Min Act: -0.1700
Data Index: 4213097 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5008. Min Range: -5.5008
Max Act: 5.3758. Min Act: -0.1700
Data Index: 1088421 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5008. Min Range: -5.5008
Max Act: 5.3758. Min Act: -0.1700
Data Index: 3765077 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5008. Min Range: -5.5008
Max Act: 5.3446. Min Act: -0.1700
Data Index: 890892 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5008. Min Range: -5.5008
Max Act: 5.3133. Min Act: -0.1700
Data Index: 6494978 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5008. Min Range: -5.5008
Max Act: 5.3446. Min Act: -0.1700
Data Index: 7444190 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5008. Min Range: -5.5008
Max Act: 5.3446. Min Act: -0.1700
Data Index: 3703942 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5008. Min Range: -5.5008
Max Act: 5.3133. Min Act: -0.1700
Data Index: 6579364 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5008. Min Range: -5.5008
Max Act: 5.3133. Min Act: -0.1700
Data Index: 1245263 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5008. Min Range: -5.5008
Max Act: 5.2821. Min Act: -0.1700
Data Index: 6589300 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5008. Min Range: -5.5008
Max Act: 5.2821. Min Act: -0.1700
Data Index: 3296593 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #19