Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3602 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0777. Min Range: -4.0777
Max Act: 4.0777. Min Act: -0.1700
Data Index: 2561661 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0777. Min Range: -4.0777
Max Act: 4.0465. Min Act: -0.1700
Data Index: 8131634 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0777. Min Range: -4.0777
Max Act: 4.0465. Min Act: -0.1700
Data Index: 6715483 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0777. Min Range: -4.0777
Max Act: 4.0465. Min Act: -0.1700
Data Index: 5991744 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0777. Min Range: -4.0777
Max Act: 4.0152. Min Act: -0.1696
Data Index: 8568276 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0777. Min Range: -4.0777
Max Act: 4.0152. Min Act: -0.1700
Data Index: 2968225 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0777. Min Range: -4.0777
Max Act: 4.0152. Min Act: -0.1699
Data Index: 5385282 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0777. Min Range: -4.0777
Max Act: 4.0152. Min Act: -0.1700
Data Index: 1725712 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0777. Min Range: -4.0777
Max Act: 4.0152. Min Act: -0.1700
Data Index: 5513978 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0777. Min Range: -4.0777
Max Act: 3.9840. Min Act: -0.1700
Data Index: 866636 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0777. Min Range: -4.0777
Max Act: 4.0152. Min Act: -0.1700
Data Index: 6056477 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0777. Min Range: -4.0777
Max Act: 4.0152. Min Act: -0.1700
Data Index: 8497243 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0777. Min Range: -4.0777
Max Act: 4.0152. Min Act: -0.1700
Data Index: 4754210 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0777. Min Range: -4.0777
Max Act: 4.0152. Min Act: -0.1700
Data Index: 7771918 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0777. Min Range: -4.0777
Max Act: 3.9840. Min Act: -0.1700
Data Index: 425238 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0777. Min Range: -4.0777
Max Act: 3.9840. Min Act: -0.1700
Data Index: 974191 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0777. Min Range: -4.0777
Max Act: 3.9840. Min Act: -0.1700
Data Index: 1930427 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0777. Min Range: -4.0777
Max Act: 3.9840. Min Act: -0.1700
Data Index: 6255744 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0777. Min Range: -4.0777
Max Act: 3.9840. Min Act: -0.1700
Data Index: 6758600 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0777. Min Range: -4.0777
Max Act: 3.9840. Min Act: -0.1700
Data Index: 7273723 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19