Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2432 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2859. Min Range: -6.2859
Max Act: 6.2859. Min Act: -0.1700
Data Index: 4560850 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2859. Min Range: -6.2859
Max Act: 6.2547. Min Act: -0.1700
Data Index: 2572151 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2859. Min Range: -6.2859
Max Act: 6.2547. Min Act: -0.1700
Data Index: 8087715 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2859. Min Range: -6.2859
Max Act: 6.2234. Min Act: -0.1700
Data Index: 5263526 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2859. Min Range: -6.2859
Max Act: 6.1922. Min Act: -0.1700
Data Index: 2192393 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2859. Min Range: -6.2859
Max Act: 6.1922. Min Act: -0.1700
Data Index: 1621661 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2859. Min Range: -6.2859
Max Act: 6.1922. Min Act: -0.1700
Data Index: 265688 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2859. Min Range: -6.2859
Max Act: 6.1922. Min Act: -0.1700
Data Index: 7921412 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2859. Min Range: -6.2859
Max Act: 6.1922. Min Act: -0.1700
Data Index: 2955080 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2859. Min Range: -6.2859
Max Act: 6.1922. Min Act: -0.1700
Data Index: 7654583 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2859. Min Range: -6.2859
Max Act: 6.1922. Min Act: -0.1700
Data Index: 1085438 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2859. Min Range: -6.2859
Max Act: 6.1922. Min Act: -0.1700
Data Index: 7187974 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2859. Min Range: -6.2859
Max Act: 6.1922. Min Act: -0.1700
Data Index: 1075293 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2859. Min Range: -6.2859
Max Act: 6.1922. Min Act: -0.1700
Data Index: 7176683 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2859. Min Range: -6.2859
Max Act: 6.1922. Min Act: -0.1700
Data Index: 2595277 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2859. Min Range: -6.2859
Max Act: 6.1922. Min Act: -0.1700
Data Index: 97833 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2859. Min Range: -6.2859
Max Act: 6.1922. Min Act: -0.1700
Data Index: 5670673 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2859. Min Range: -6.2859
Max Act: 6.1609. Min Act: -0.1700
Data Index: 4586815 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2859. Min Range: -6.2859
Max Act: 6.1609. Min Act: -0.1700
Data Index: 127111 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2859. Min Range: -6.2859
Max Act: 6.1609. Min Act: -0.1700
Data Index: 5255095 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19