Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3514 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9545. Min Range: -4.9545
Max Act: 4.9545. Min Act: -0.1700
Data Index: 1303999 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9545. Min Range: -4.9545
Max Act: 4.9545. Min Act: -0.1700
Data Index: 2861162 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9545. Min Range: -4.9545
Max Act: 4.8295. Min Act: -0.1700
Data Index: 5175994 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9545. Min Range: -4.9545
Max Act: 4.8607. Min Act: -0.1699
Data Index: 8788642 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9545. Min Range: -4.9545
Max Act: 4.8295. Min Act: -0.1700
Data Index: 7053722 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9545. Min Range: -4.9545
Max Act: 4.7982. Min Act: -0.1700
Data Index: 3757379 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9545. Min Range: -4.9545
Max Act: 4.7982. Min Act: -0.1700
Data Index: 7786637 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9545. Min Range: -4.9545
Max Act: 4.7982. Min Act: -0.1700
Data Index: 7842114 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9545. Min Range: -4.9545
Max Act: 4.7670. Min Act: -0.1700
Data Index: 3001925 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9545. Min Range: -4.9545
Max Act: 4.7982. Min Act: -0.1700
Data Index: 8756327 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9545. Min Range: -4.9545
Max Act: 4.7670. Min Act: -0.1700
Data Index: 1774027 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9545. Min Range: -4.9545
Max Act: 4.7670. Min Act: -0.1700
Data Index: 5933241 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9545. Min Range: -4.9545
Max Act: 4.7357. Min Act: -0.1700
Data Index: 4583548 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9545. Min Range: -4.9545
Max Act: 4.7357. Min Act: -0.1700
Data Index: 4083564 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9545. Min Range: -4.9545
Max Act: 4.7045. Min Act: -0.1700
Data Index: 4029226 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9545. Min Range: -4.9545
Max Act: 4.7357. Min Act: -0.1700
Data Index: 8646170 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9545. Min Range: -4.9545
Max Act: 4.7357. Min Act: -0.1700
Data Index: 5788226 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9545. Min Range: -4.9545
Max Act: 4.7045. Min Act: -0.1700
Data Index: 8631306 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9545. Min Range: -4.9545
Max Act: 4.7045. Min Act: -0.1700
Data Index: 7887759 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9545. Min Range: -4.9545
Max Act: 4.7045. Min Act: -0.1700
Data Index: 6809499 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #19