Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5263 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4938. Min Range: -3.4938
Max Act: 3.4938. Min Act: -0.1700
Data Index: 5183626 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4938. Min Range: -3.4938
Max Act: 3.4938. Min Act: -0.1700
Data Index: 6177324 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4938. Min Range: -3.4938
Max Act: 3.4938. Min Act: -0.1700
Data Index: 6932136 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4938. Min Range: -3.4938
Max Act: 3.4625. Min Act: -0.1700
Data Index: 215815 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4938. Min Range: -3.4938
Max Act: 3.4625. Min Act: -0.1700
Data Index: 7268289 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4938. Min Range: -3.4938
Max Act: 3.4311. Min Act: -0.1700
Data Index: 7746600 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4938. Min Range: -3.4938
Max Act: 3.4311. Min Act: -0.1700
Data Index: 4040178 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4938. Min Range: -3.4938
Max Act: 3.4311. Min Act: -0.1700
Data Index: 1594737 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4938. Min Range: -3.4938
Max Act: 3.3998. Min Act: -0.1700
Data Index: 5416171 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4938. Min Range: -3.4938
Max Act: 3.3998. Min Act: -0.1700
Data Index: 1829953 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4938. Min Range: -3.4938
Max Act: 3.3998. Min Act: -0.1700
Data Index: 8569812 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4938. Min Range: -3.4938
Max Act: 3.3998. Min Act: -0.1700
Data Index: 7374531 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4938. Min Range: -3.4938
Max Act: 3.3998. Min Act: -0.1700
Data Index: 1715174 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4938. Min Range: -3.4938
Max Act: 3.3998. Min Act: -0.1700
Data Index: 6872879 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4938. Min Range: -3.4938
Max Act: 3.3998. Min Act: -0.1700
Data Index: 6547965 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4938. Min Range: -3.4938
Max Act: 3.3998. Min Act: -0.1700
Data Index: 6243027 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4938. Min Range: -3.4938
Max Act: 3.3998. Min Act: -0.1700
Data Index: 6198307 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4938. Min Range: -3.4938
Max Act: 3.3998. Min Act: -0.1700
Data Index: 1392457 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4938. Min Range: -3.4938
Max Act: 3.3998. Min Act: -0.1700
Data Index: 5672772 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4938. Min Range: -3.4938
Max Act: 3.3684. Min Act: -0.1700
Data Index: 227279 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19