Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2777 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2692. Min Range: -4.2692
Max Act: 4.2692. Min Act: -0.1700
Data Index: 8493833 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2692. Min Range: -4.2692
Max Act: 4.2380. Min Act: -0.1700
Data Index: 8727054 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2692. Min Range: -4.2692
Max Act: 4.2067. Min Act: -0.1700
Data Index: 5032780 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2692. Min Range: -4.2692
Max Act: 4.2067. Min Act: -0.1700
Data Index: 4035829 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2692. Min Range: -4.2692
Max Act: 4.2067. Min Act: -0.1700
Data Index: 3608332 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2692. Min Range: -4.2692
Max Act: 4.1755. Min Act: -0.1700
Data Index: 7681406 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2692. Min Range: -4.2692
Max Act: 4.1755. Min Act: -0.1700
Data Index: 7772253 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2692. Min Range: -4.2692
Max Act: 4.1755. Min Act: -0.1700
Data Index: 226827 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2692. Min Range: -4.2692
Max Act: 4.1755. Min Act: -0.1700
Data Index: 7406353 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2692. Min Range: -4.2692
Max Act: 4.1442. Min Act: -0.1700
Data Index: 7462050 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2692. Min Range: -4.2692
Max Act: 4.1442. Min Act: -0.1700
Data Index: 1688770 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2692. Min Range: -4.2692
Max Act: 4.1442. Min Act: -0.1700
Data Index: 7367236 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2692. Min Range: -4.2692
Max Act: 4.1442. Min Act: -0.1700
Data Index: 7816637 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2692. Min Range: -4.2692
Max Act: 4.1442. Min Act: -0.1700
Data Index: 7326358 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2692. Min Range: -4.2692
Max Act: 4.1442. Min Act: -0.1700
Data Index: 8392693 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2692. Min Range: -4.2692
Max Act: 4.1442. Min Act: -0.1700
Data Index: 2160049 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2692. Min Range: -4.2692
Max Act: 4.1442. Min Act: -0.1700
Data Index: 7095722 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2692. Min Range: -4.2692
Max Act: 4.1442. Min Act: -0.1700
Data Index: 7030632 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2692. Min Range: -4.2692
Max Act: 4.1130. Min Act: -0.1700
Data Index: 6490107 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2692. Min Range: -4.2692
Max Act: 4.1130. Min Act: -0.1700
Data Index: 4870933 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19