Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2977 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0579. Min Range: -4.0579
Max Act: 4.0579. Min Act: -0.1700
Data Index: 4936076 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0579. Min Range: -4.0579
Max Act: 4.0579. Min Act: -0.1700
Data Index: 8701644 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0579. Min Range: -4.0579
Max Act: 4.0267. Min Act: -0.1700
Data Index: 2317808 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0579. Min Range: -4.0579
Max Act: 3.9954. Min Act: -0.1700
Data Index: 6737821 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0579. Min Range: -4.0579
Max Act: 3.9954. Min Act: -0.1700
Data Index: 6112801 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0579. Min Range: -4.0579
Max Act: 3.9954. Min Act: -0.1700
Data Index: 7381346 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0579. Min Range: -4.0579
Max Act: 3.9954. Min Act: -0.1700
Data Index: 2844561 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0579. Min Range: -4.0579
Max Act: 3.9954. Min Act: -0.1700
Data Index: 8726202 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0579. Min Range: -4.0579
Max Act: 3.9642. Min Act: -0.1700
Data Index: 8829228 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0579. Min Range: -4.0579
Max Act: 3.9329. Min Act: -0.1700
Data Index: 4467777 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0579. Min Range: -4.0579
Max Act: 3.9642. Min Act: -0.1700
Data Index: 732652 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0579. Min Range: -4.0579
Max Act: 3.9642. Min Act: -0.1700
Data Index: 8724714 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0579. Min Range: -4.0579
Max Act: 3.9642. Min Act: -0.1700
Data Index: 68484 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0579. Min Range: -4.0579
Max Act: 3.9642. Min Act: -0.1700
Data Index: 2559907 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0579. Min Range: -4.0579
Max Act: 3.9642. Min Act: -0.1700
Data Index: 2365710 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0579. Min Range: -4.0579
Max Act: 3.9329. Min Act: -0.1700
Data Index: 634578 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0579. Min Range: -4.0579
Max Act: 3.9329. Min Act: -0.1700
Data Index: 5251676 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0579. Min Range: -4.0579
Max Act: 3.9329. Min Act: -0.1700
Data Index: 1802266 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0579. Min Range: -4.0579
Max Act: 3.9329. Min Act: -0.1700
Data Index: 1320474 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0579. Min Range: -4.0579
Max Act: 3.9329. Min Act: -0.1700
Data Index: 1835906 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19