Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2418 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9741. Min Range: -2.9741
Max Act: 2.9741. Min Act: -0.1700
Data Index: 771320 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9741. Min Range: -2.9741
Max Act: 2.9424. Min Act: -0.1700
Data Index: 2660864 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9741. Min Range: -2.9741
Max Act: 2.9424. Min Act: -0.1700
Data Index: 4647115 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9741. Min Range: -2.9741
Max Act: 2.8949. Min Act: -0.1700
Data Index: 5830306 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9741. Min Range: -2.9741
Max Act: 2.8790. Min Act: -0.1700
Data Index: 6227601 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9741. Min Range: -2.9741
Max Act: 2.8949. Min Act: -0.1700
Data Index: 1473091 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9741. Min Range: -2.9741
Max Act: 2.8631. Min Act: -0.1700
Data Index: 3498648 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9741. Min Range: -2.9741
Max Act: 2.8631. Min Act: -0.1700
Data Index: 5574372 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9741. Min Range: -2.9741
Max Act: 2.8790. Min Act: -0.1700
Data Index: 3090592 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9741. Min Range: -2.9741
Max Act: 2.8472. Min Act: -0.1700
Data Index: 487180 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9741. Min Range: -2.9741
Max Act: 2.8472. Min Act: -0.1700
Data Index: 1324496 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9741. Min Range: -2.9741
Max Act: 2.8472. Min Act: -0.1700
Data Index: 4565958 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9741. Min Range: -2.9741
Max Act: 2.8472. Min Act: -0.1700
Data Index: 254130 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9741. Min Range: -2.9741
Max Act: 2.8472. Min Act: -0.1700
Data Index: 4763665 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9741. Min Range: -2.9741
Max Act: 2.8472. Min Act: -0.1700
Data Index: 2196391 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9741. Min Range: -2.9741
Max Act: 2.8472. Min Act: -0.1700
Data Index: 1240927 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9741. Min Range: -2.9741
Max Act: 2.8472. Min Act: -0.1700
Data Index: 1054796 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9741. Min Range: -2.9741
Max Act: 2.8472. Min Act: -0.1700
Data Index: 2764313 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9741. Min Range: -2.9741
Max Act: 2.8472. Min Act: -0.1700
Data Index: 3412493 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9741. Min Range: -2.9741
Max Act: 2.8472. Min Act: -0.1700
Data Index: 4657517 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19