Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3361 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.6066. Min Range: -12.6066
Max Act: 12.6066. Min Act: -0.1700
Data Index: 5874741 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.6066. Min Range: -12.6066
Max Act: 12.4816. Min Act: -0.1700
Data Index: 520462 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.6066. Min Range: -12.6066
Max Act: 12.4816. Min Act: -0.1700
Data Index: 7323160 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.6066. Min Range: -12.6066
Max Act: 12.4191. Min Act: -0.1700
Data Index: 426416 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.6066. Min Range: -12.6066
Max Act: 12.3566. Min Act: -0.1700
Data Index: 3193109 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.6066. Min Range: -12.6066
Max Act: 12.3566. Min Act: -0.1700
Data Index: 515785 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.6066. Min Range: -12.6066
Max Act: 12.2941. Min Act: -0.1700
Data Index: 7763133 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.6066. Min Range: -12.6066
Max Act: 12.2316. Min Act: -0.1700
Data Index: 1523222 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.6066. Min Range: -12.6066
Max Act: 12.2316. Min Act: -0.1700
Data Index: 8128183 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.6066. Min Range: -12.6066
Max Act: 12.2316. Min Act: -0.1700
Data Index: 4115949 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.6066. Min Range: -12.6066
Max Act: 12.2316. Min Act: -0.1700
Data Index: 8366262 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.6066. Min Range: -12.6066
Max Act: 12.2941. Min Act: -0.1700
Data Index: 1022754 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.6066. Min Range: -12.6066
Max Act: 12.2316. Min Act: -0.1700
Data Index: 2804069 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.6066. Min Range: -12.6066
Max Act: 12.1691. Min Act: -0.1700
Data Index: 4244716 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.6066. Min Range: -12.6066
Max Act: 12.1691. Min Act: -0.1700
Data Index: 2171442 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.6066. Min Range: -12.6066
Max Act: 12.1691. Min Act: -0.1700
Data Index: 6127237 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.6066. Min Range: -12.6066
Max Act: 12.1691. Min Act: -0.1700
Data Index: 852722 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.6066. Min Range: -12.6066
Max Act: 12.1691. Min Act: -0.1700
Data Index: 6583004 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.6066. Min Range: -12.6066
Max Act: 12.0441. Min Act: -0.1700
Data Index: 3242691 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.6066. Min Range: -12.6066
Max Act: 12.0441. Min Act: -0.1700
Data Index: 6992344 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19