Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1011 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1103. Min Range: -5.1103
Max Act: 5.1103. Min Act: -0.1700
Data Index: 2205401 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1103. Min Range: -5.1103
Max Act: 5.1103. Min Act: -0.1700
Data Index: 398600 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1103. Min Range: -5.1103
Max Act: 5.0790. Min Act: -0.1700
Data Index: 5306431 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1103. Min Range: -5.1103
Max Act: 5.1103. Min Act: -0.1700
Data Index: 4579617 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1103. Min Range: -5.1103
Max Act: 5.0478. Min Act: -0.1700
Data Index: 2600588 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1103. Min Range: -5.1103
Max Act: 5.0478. Min Act: -0.1700
Data Index: 8831823 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1103. Min Range: -5.1103
Max Act: 4.9853. Min Act: -0.1700
Data Index: 1914763 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1103. Min Range: -5.1103
Max Act: 4.9540. Min Act: -0.1700
Data Index: 1969392 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1103. Min Range: -5.1103
Max Act: 4.9540. Min Act: -0.1700
Data Index: 350613 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1103. Min Range: -5.1103
Max Act: 4.9228. Min Act: -0.1700
Data Index: 3410817 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1103. Min Range: -5.1103
Max Act: 4.9228. Min Act: -0.1700
Data Index: 2228266 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1103. Min Range: -5.1103
Max Act: 4.8915. Min Act: -0.1700
Data Index: 7343512 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1103. Min Range: -5.1103
Max Act: 4.8915. Min Act: -0.1700
Data Index: 5529389 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1103. Min Range: -5.1103
Max Act: 4.8915. Min Act: -0.1700
Data Index: 6609703 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1103. Min Range: -5.1103
Max Act: 4.8915. Min Act: -0.1700
Data Index: 2891132 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1103. Min Range: -5.1103
Max Act: 4.8603. Min Act: -0.1700
Data Index: 1164468 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1103. Min Range: -5.1103
Max Act: 4.8603. Min Act: -0.1700
Data Index: 6142358 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1103. Min Range: -5.1103
Max Act: 4.8603. Min Act: -0.1700
Data Index: 3772331 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1103. Min Range: -5.1103
Max Act: 4.8290. Min Act: -0.1700
Data Index: 5121890 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1103. Min Range: -5.1103
Max Act: 4.8290. Min Act: -0.1700
Data Index: 940483 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19