Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2789 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3120. Min Range: -5.3120
Max Act: 5.3120. Min Act: -0.1700
Data Index: 4045417 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3120. Min Range: -5.3120
Max Act: 5.3120. Min Act: -0.1699
Data Index: 2212036 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3120. Min Range: -5.3120
Max Act: 5.2495. Min Act: -0.1700
Data Index: 2415264 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3120. Min Range: -5.3120
Max Act: 5.2183. Min Act: -0.1700
Data Index: 3366805 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3120. Min Range: -5.3120
Max Act: 5.2183. Min Act: -0.1700
Data Index: 5207913 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3120. Min Range: -5.3120
Max Act: 5.1870. Min Act: -0.1700
Data Index: 7565274 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3120. Min Range: -5.3120
Max Act: 5.1870. Min Act: -0.1700
Data Index: 2855200 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3120. Min Range: -5.3120
Max Act: 5.1870. Min Act: -0.1700
Data Index: 4395476 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3120. Min Range: -5.3120
Max Act: 5.1558. Min Act: -0.1700
Data Index: 8096848 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3120. Min Range: -5.3120
Max Act: 5.1245. Min Act: -0.1700
Data Index: 5904089 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3120. Min Range: -5.3120
Max Act: 5.1245. Min Act: -0.1700
Data Index: 3691755 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3120. Min Range: -5.3120
Max Act: 5.1245. Min Act: -0.1700
Data Index: 4374725 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3120. Min Range: -5.3120
Max Act: 5.0933. Min Act: -0.1700
Data Index: 878340 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3120. Min Range: -5.3120
Max Act: 5.1245. Min Act: -0.1700
Data Index: 549926 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3120. Min Range: -5.3120
Max Act: 5.1245. Min Act: -0.1700
Data Index: 8432789 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3120. Min Range: -5.3120
Max Act: 5.1245. Min Act: -0.1700
Data Index: 806351 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3120. Min Range: -5.3120
Max Act: 5.1245. Min Act: -0.1700
Data Index: 1405057 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3120. Min Range: -5.3120
Max Act: 5.0933. Min Act: -0.1700
Data Index: 1812659 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3120. Min Range: -5.3120
Max Act: 5.0620. Min Act: -0.1699
Data Index: 1714846 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3120. Min Range: -5.3120
Max Act: 5.0620. Min Act: -0.1700
Data Index: 1987158 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19