Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2648 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5039. Min Range: -8.5039
Max Act: 8.5039. Min Act: -0.1700
Data Index: 2047281 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5039. Min Range: -8.5039
Max Act: 8.3789. Min Act: -0.1700
Data Index: 4098716 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5039. Min Range: -8.5039
Max Act: 8.3164. Min Act: -0.1700
Data Index: 5979691 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5039. Min Range: -8.5039
Max Act: 8.1914. Min Act: -0.1700
Data Index: 716285 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5039. Min Range: -8.5039
Max Act: 8.0664. Min Act: -0.1700
Data Index: 5286610 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5039. Min Range: -8.5039
Max Act: 8.0039. Min Act: -0.1700
Data Index: 5331477 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5039. Min Range: -8.5039
Max Act: 8.0039. Min Act: -0.1700
Data Index: 1541496 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5039. Min Range: -8.5039
Max Act: 7.9414. Min Act: -0.1700
Data Index: 718981 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5039. Min Range: -8.5039
Max Act: 7.8164. Min Act: -0.1700
Data Index: 972110 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5039. Min Range: -8.5039
Max Act: 7.8164. Min Act: -0.1700
Data Index: 2758301 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5039. Min Range: -8.5039
Max Act: 7.8164. Min Act: -0.1700
Data Index: 6228066 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5039. Min Range: -8.5039
Max Act: 7.8789. Min Act: -0.1700
Data Index: 4701704 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5039. Min Range: -8.5039
Max Act: 7.8164. Min Act: -0.1700
Data Index: 5401424 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5039. Min Range: -8.5039
Max Act: 7.7539. Min Act: -0.1700
Data Index: 5158196 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5039. Min Range: -8.5039
Max Act: 7.7539. Min Act: -0.1700
Data Index: 4794209 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5039. Min Range: -8.5039
Max Act: 7.7539. Min Act: -0.1700
Data Index: 7208421 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5039. Min Range: -8.5039
Max Act: 7.8164. Min Act: -0.1700
Data Index: 5328791 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5039. Min Range: -8.5039
Max Act: 7.6914. Min Act: -0.1700
Data Index: 3849377 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5039. Min Range: -8.5039
Max Act: 7.6914. Min Act: -0.1700
Data Index: 3390161 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5039. Min Range: -8.5039
Max Act: 7.6914. Min Act: -0.1700
Data Index: 2973172 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #19