Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2717 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1620. Min Range: -6.1620
Max Act: 6.1620. Min Act: -0.1700
Data Index: 7876599 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1620. Min Range: -6.1620
Max Act: 5.8807. Min Act: -0.1700
Data Index: 2027992 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1620. Min Range: -6.1620
Max Act: 5.8182. Min Act: -0.1700
Data Index: 7536897 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1620. Min Range: -6.1620
Max Act: 5.8182. Min Act: -0.1700
Data Index: 5458570 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1620. Min Range: -6.1620
Max Act: 5.7870. Min Act: -0.1700
Data Index: 4602275 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1620. Min Range: -6.1620
Max Act: 5.7870. Min Act: -0.1700
Data Index: 2071182 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1620. Min Range: -6.1620
Max Act: 5.7557. Min Act: -0.1700
Data Index: 4362639 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1620. Min Range: -6.1620
Max Act: 5.7557. Min Act: -0.1700
Data Index: 6775690 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1620. Min Range: -6.1620
Max Act: 5.7245. Min Act: -0.1700
Data Index: 375565 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1620. Min Range: -6.1620
Max Act: 5.7557. Min Act: -0.1700
Data Index: 3816620 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1620. Min Range: -6.1620
Max Act: 5.7557. Min Act: -0.1700
Data Index: 8153578 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1620. Min Range: -6.1620
Max Act: 5.7245. Min Act: -0.1700
Data Index: 8757604 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1620. Min Range: -6.1620
Max Act: 5.7245. Min Act: -0.1700
Data Index: 3695848 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1620. Min Range: -6.1620
Max Act: 5.7245. Min Act: -0.1700
Data Index: 5218706 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1620. Min Range: -6.1620
Max Act: 5.7245. Min Act: -0.1700
Data Index: 7734244 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1620. Min Range: -6.1620
Max Act: 5.7245. Min Act: -0.1700
Data Index: 5387257 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1620. Min Range: -6.1620
Max Act: 5.6932. Min Act: -0.1700
Data Index: 3664227 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1620. Min Range: -6.1620
Max Act: 5.7245. Min Act: -0.1700
Data Index: 6645463 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1620. Min Range: -6.1620
Max Act: 5.6932. Min Act: -0.1700
Data Index: 361730 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1620. Min Range: -6.1620
Max Act: 5.6932. Min Act: -0.1700
Data Index: 7427964 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #19