Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 271 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5683. Min Range: -6.5683
Max Act: 6.5683. Min Act: -0.1700
Data Index: 2904563 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5683. Min Range: -6.5683
Max Act: 6.1933. Min Act: -0.1700
Data Index: 8454305 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5683. Min Range: -6.5683
Max Act: 6.1933. Min Act: -0.1700
Data Index: 6922933 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5683. Min Range: -6.5683
Max Act: 6.1308. Min Act: -0.1700
Data Index: 6474501 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5683. Min Range: -6.5683
Max Act: 6.0683. Min Act: -0.1700
Data Index: 188917 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5683. Min Range: -6.5683
Max Act: 5.9433. Min Act: -0.1700
Data Index: 8192454 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5683. Min Range: -6.5683
Max Act: 5.9745. Min Act: -0.1700
Data Index: 2500509 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5683. Min Range: -6.5683
Max Act: 5.8495. Min Act: -0.1700
Data Index: 6385880 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5683. Min Range: -6.5683
Max Act: 5.8183. Min Act: -0.1700
Data Index: 7104789 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5683. Min Range: -6.5683
Max Act: 5.8183. Min Act: -0.1700
Data Index: 2635694 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5683. Min Range: -6.5683
Max Act: 5.7870. Min Act: -0.1700
Data Index: 3761173 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5683. Min Range: -6.5683
Max Act: 5.7870. Min Act: -0.1700
Data Index: 8286635 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5683. Min Range: -6.5683
Max Act: 5.7870. Min Act: -0.1700
Data Index: 8115509 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5683. Min Range: -6.5683
Max Act: 5.7870. Min Act: -0.1700
Data Index: 94118 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5683. Min Range: -6.5683
Max Act: 5.7558. Min Act: -0.1700
Data Index: 1895819 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5683. Min Range: -6.5683
Max Act: 5.7245. Min Act: -0.1700
Data Index: 4391503 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5683. Min Range: -6.5683
Max Act: 5.7245. Min Act: -0.1700
Data Index: 2280865 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5683. Min Range: -6.5683
Max Act: 5.7245. Min Act: -0.1700
Data Index: 7306685 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5683. Min Range: -6.5683
Max Act: 5.7245. Min Act: -0.1700
Data Index: 4224866 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5683. Min Range: -6.5683
Max Act: 5.6933. Min Act: -0.1700
Data Index: 4471681 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #19