Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2892 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4076. Min Range: -4.4076
Max Act: 4.4076. Min Act: -0.1700
Data Index: 5180772 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4076. Min Range: -4.4076
Max Act: 4.3139. Min Act: -0.1700
Data Index: 6463227 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4076. Min Range: -4.4076
Max Act: 4.1576. Min Act: -0.1700
Data Index: 3006420 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4076. Min Range: -4.4076
Max Act: 4.0638. Min Act: -0.1700
Data Index: 8392764 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4076. Min Range: -4.4076
Max Act: 4.0326. Min Act: -0.1700
Data Index: 5260587 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4076. Min Range: -4.4076
Max Act: 4.0013. Min Act: -0.1700
Data Index: 8744801 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4076. Min Range: -4.4076
Max Act: 4.0013. Min Act: -0.1700
Data Index: 4465683 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4076. Min Range: -4.4076
Max Act: 3.9700. Min Act: -0.1700
Data Index: 4804806 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4076. Min Range: -4.4076
Max Act: 3.9700. Min Act: -0.1700
Data Index: 4804809 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4076. Min Range: -4.4076
Max Act: 3.9700. Min Act: -0.1700
Data Index: 5327865 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4076. Min Range: -4.4076
Max Act: 3.9388. Min Act: -0.1700
Data Index: 2094065 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4076. Min Range: -4.4076
Max Act: 3.8763. Min Act: -0.1700
Data Index: 1566628 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4076. Min Range: -4.4076
Max Act: 3.8450. Min Act: -0.1700
Data Index: 153238 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4076. Min Range: -4.4076
Max Act: 3.8763. Min Act: -0.1700
Data Index: 2024809 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4076. Min Range: -4.4076
Max Act: 3.8763. Min Act: -0.1700
Data Index: 1867346 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4076. Min Range: -4.4076
Max Act: 3.8763. Min Act: -0.1700
Data Index: 6163440 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4076. Min Range: -4.4076
Max Act: 3.8763. Min Act: -0.1700
Data Index: 5859847 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4076. Min Range: -4.4076
Max Act: 3.8450. Min Act: -0.1700
Data Index: 471300 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4076. Min Range: -4.4076
Max Act: 3.8450. Min Act: -0.1700
Data Index: 5947025 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4076. Min Range: -4.4076
Max Act: 3.8450. Min Act: -0.1700
Data Index: 6324098 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #19