Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3842 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9345. Min Range: -6.9345
Max Act: 6.9345. Min Act: -0.1700
Data Index: 2627823 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9345. Min Range: -6.9345
Max Act: 6.7783. Min Act: -0.1700
Data Index: 6130751 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9345. Min Range: -6.9345
Max Act: 6.4970. Min Act: -0.1700
Data Index: 422297 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9345. Min Range: -6.9345
Max Act: 6.4658. Min Act: -0.1700
Data Index: 776103 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9345. Min Range: -6.9345
Max Act: 6.4658. Min Act: -0.1700
Data Index: 2590881 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9345. Min Range: -6.9345
Max Act: 6.4033. Min Act: -0.1700
Data Index: 7300687 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9345. Min Range: -6.9345
Max Act: 6.4033. Min Act: -0.1700
Data Index: 4724756 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9345. Min Range: -6.9345
Max Act: 6.4345. Min Act: -0.1700
Data Index: 4023010 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9345. Min Range: -6.9345
Max Act: 6.4033. Min Act: -0.1700
Data Index: 5508899 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9345. Min Range: -6.9345
Max Act: 6.3408. Min Act: -0.1700
Data Index: 4321566 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9345. Min Range: -6.9345
Max Act: 6.3408. Min Act: -0.1700
Data Index: 7951384 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9345. Min Range: -6.9345
Max Act: 6.3408. Min Act: -0.1699
Data Index: 3085262 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9345. Min Range: -6.9345
Max Act: 6.3408. Min Act: -0.1700
Data Index: 6216073 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9345. Min Range: -6.9345
Max Act: 6.3408. Min Act: -0.1700
Data Index: 3606823 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9345. Min Range: -6.9345
Max Act: 6.2783. Min Act: -0.1700
Data Index: 2525592 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9345. Min Range: -6.9345
Max Act: 6.2783. Min Act: -0.1700
Data Index: 4823575 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9345. Min Range: -6.9345
Max Act: 6.2783. Min Act: -0.1700
Data Index: 6414557 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9345. Min Range: -6.9345
Max Act: 6.2470. Min Act: -0.1700
Data Index: 2078552 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9345. Min Range: -6.9345
Max Act: 6.2470. Min Act: -0.1700
Data Index: 7814150 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9345. Min Range: -6.9345
Max Act: 6.2470. Min Act: -0.1700
Data Index: 3957839 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #19