Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4091 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3323. Min Range: -4.3323
Max Act: 4.3323. Min Act: -0.1700
Data Index: 2640750 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3323. Min Range: -4.3323
Max Act: 4.3323. Min Act: -0.1700
Data Index: 1892677 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3323. Min Range: -4.3323
Max Act: 4.3011. Min Act: -0.1700
Data Index: 7615987 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3323. Min Range: -4.3323
Max Act: 4.2698. Min Act: -0.1696
Data Index: 4647918 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3323. Min Range: -4.3323
Max Act: 4.2698. Min Act: -0.1700
Data Index: 8831619 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3323. Min Range: -4.3323
Max Act: 4.2698. Min Act: -0.1700
Data Index: 957276 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3323. Min Range: -4.3323
Max Act: 4.2698. Min Act: -0.1700
Data Index: 1824479 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3323. Min Range: -4.3323
Max Act: 4.2698. Min Act: -0.1700
Data Index: 2658278 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3323. Min Range: -4.3323
Max Act: 4.2386. Min Act: -0.1700
Data Index: 5692536 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3323. Min Range: -4.3323
Max Act: 4.2386. Min Act: -0.1700
Data Index: 5442064 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3323. Min Range: -4.3323
Max Act: 4.2386. Min Act: -0.1700
Data Index: 8676684 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3323. Min Range: -4.3323
Max Act: 4.2386. Min Act: -0.1700
Data Index: 5998564 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3323. Min Range: -4.3323
Max Act: 4.2386. Min Act: -0.1700
Data Index: 4649152 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3323. Min Range: -4.3323
Max Act: 4.2386. Min Act: -0.1700
Data Index: 458530 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3323. Min Range: -4.3323
Max Act: 4.2073. Min Act: -0.1700
Data Index: 4685032 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3323. Min Range: -4.3323
Max Act: 4.2073. Min Act: -0.1700
Data Index: 7707494 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3323. Min Range: -4.3323
Max Act: 4.2073. Min Act: -0.1700
Data Index: 8192014 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3323. Min Range: -4.3323
Max Act: 4.2073. Min Act: -0.1700
Data Index: 465174 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3323. Min Range: -4.3323
Max Act: 4.2073. Min Act: -0.1700
Data Index: 8779563 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3323. Min Range: -4.3323
Max Act: 4.2073. Min Act: -0.1700
Data Index: 1721718 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19