Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2361 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3657. Min Range: -3.3657
Max Act: 3.3657. Min Act: -0.1700
Data Index: 4727488 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3657. Min Range: -3.3657
Max Act: 3.3657. Min Act: -0.1700
Data Index: 3618647 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3657. Min Range: -3.3657
Max Act: 3.3657. Min Act: -0.1700
Data Index: 3963606 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3657. Min Range: -3.3657
Max Act: 3.3344. Min Act: -0.1700
Data Index: 8775453 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3657. Min Range: -3.3657
Max Act: 3.3344. Min Act: -0.1700
Data Index: 25365 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3657. Min Range: -3.3657
Max Act: 3.3344. Min Act: -0.1700
Data Index: 2561763 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3657. Min Range: -3.3657
Max Act: 3.3344. Min Act: -0.1700
Data Index: 2515225 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3657. Min Range: -3.3657
Max Act: 3.3344. Min Act: -0.1700
Data Index: 2316850 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3657. Min Range: -3.3657
Max Act: 3.3344. Min Act: -0.1700
Data Index: 4086357 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3657. Min Range: -3.3657
Max Act: 3.3344. Min Act: -0.1700
Data Index: 1885842 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3657. Min Range: -3.3657
Max Act: 3.3344. Min Act: -0.1700
Data Index: 8499829 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3657. Min Range: -3.3657
Max Act: 3.3344. Min Act: -0.1700
Data Index: 2964118 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3657. Min Range: -3.3657
Max Act: 3.3030. Min Act: -0.1700
Data Index: 5797795 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3657. Min Range: -3.3657
Max Act: 3.3344. Min Act: -0.1700
Data Index: 5039294 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3657. Min Range: -3.3657
Max Act: 3.3344. Min Act: -0.1700
Data Index: 4852825 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3657. Min Range: -3.3657
Max Act: 3.3030. Min Act: -0.1700
Data Index: 4249330 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3657. Min Range: -3.3657
Max Act: 3.3030. Min Act: -0.1700
Data Index: 2188306 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3657. Min Range: -3.3657
Max Act: 3.3030. Min Act: -0.1700
Data Index: 4253711 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3657. Min Range: -3.3657
Max Act: 3.3030. Min Act: -0.1700
Data Index: 2527587 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3657. Min Range: -3.3657
Max Act: 3.3030. Min Act: -0.1700
Data Index: 1405246 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19