Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 427 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9616. Min Range: -5.9616
Max Act: 5.9616. Min Act: -0.1700
Data Index: 4298851 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9616. Min Range: -5.9616
Max Act: 5.7741. Min Act: -0.1700
Data Index: 505742 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9616. Min Range: -5.9616
Max Act: 5.7741. Min Act: -0.1700
Data Index: 4298837 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9616. Min Range: -5.9616
Max Act: 5.5553. Min Act: -0.1700
Data Index: 8310558 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9616. Min Range: -5.9616
Max Act: 5.5553. Min Act: -0.1700
Data Index: 2827126 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9616. Min Range: -5.9616
Max Act: 5.4616. Min Act: -0.1700
Data Index: 4871904 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9616. Min Range: -5.9616
Max Act: 5.4303. Min Act: -0.1700
Data Index: 829517 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9616. Min Range: -5.9616
Max Act: 5.3991. Min Act: -0.1700
Data Index: 4949068 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9616. Min Range: -5.9616
Max Act: 5.3991. Min Act: -0.1700
Data Index: 3816270 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9616. Min Range: -5.9616
Max Act: 5.3678. Min Act: -0.1700
Data Index: 3030400 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9616. Min Range: -5.9616
Max Act: 5.3678. Min Act: -0.1700
Data Index: 110960 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9616. Min Range: -5.9616
Max Act: 5.3366. Min Act: -0.1700
Data Index: 7692889 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9616. Min Range: -5.9616
Max Act: 5.3053. Min Act: -0.1700
Data Index: 4140231 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9616. Min Range: -5.9616
Max Act: 5.3366. Min Act: -0.1700
Data Index: 1786051 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9616. Min Range: -5.9616
Max Act: 5.3053. Min Act: -0.1700
Data Index: 3243832 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9616. Min Range: -5.9616
Max Act: 5.3053. Min Act: -0.1700
Data Index: 527085 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9616. Min Range: -5.9616
Max Act: 5.3053. Min Act: -0.1700
Data Index: 1911625 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9616. Min Range: -5.9616
Max Act: 5.2741. Min Act: -0.1700
Data Index: 4619952 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9616. Min Range: -5.9616
Max Act: 5.2741. Min Act: -0.1700
Data Index: 2030563 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9616. Min Range: -5.9616
Max Act: 5.2741. Min Act: -0.1700
Data Index: 1677866 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #19