Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3455 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1600. Min Range: -5.1600
Max Act: 5.1600. Min Act: -0.1700
Data Index: 4889980 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1600. Min Range: -5.1600
Max Act: 5.1288. Min Act: -0.1700
Data Index: 6813733 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1600. Min Range: -5.1600
Max Act: 5.0975. Min Act: -0.1700
Data Index: 780563 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1600. Min Range: -5.1600
Max Act: 5.0350. Min Act: -0.1700
Data Index: 1685428 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1600. Min Range: -5.1600
Max Act: 5.0350. Min Act: -0.1700
Data Index: 7899864 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1600. Min Range: -5.1600
Max Act: 5.0038. Min Act: -0.1695
Data Index: 5561120 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1600. Min Range: -5.1600
Max Act: 5.0038. Min Act: -0.1700
Data Index: 8486938 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1600. Min Range: -5.1600
Max Act: 4.9725. Min Act: -0.1700
Data Index: 3225713 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1600. Min Range: -5.1600
Max Act: 4.9725. Min Act: -0.1700
Data Index: 3140784 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1600. Min Range: -5.1600
Max Act: 4.9725. Min Act: -0.1700
Data Index: 3868589 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1600. Min Range: -5.1600
Max Act: 4.9725. Min Act: -0.1700
Data Index: 6452769 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1600. Min Range: -5.1600
Max Act: 4.9725. Min Act: -0.1700
Data Index: 1793866 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1600. Min Range: -5.1600
Max Act: 4.9413. Min Act: -0.1700
Data Index: 2283246 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1600. Min Range: -5.1600
Max Act: 4.9413. Min Act: -0.1700
Data Index: 3714870 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1600. Min Range: -5.1600
Max Act: 4.9413. Min Act: -0.1700
Data Index: 1236829 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1600. Min Range: -5.1600
Max Act: 4.9413. Min Act: -0.1700
Data Index: 6151738 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1600. Min Range: -5.1600
Max Act: 4.9413. Min Act: -0.1700
Data Index: 6573079 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1600. Min Range: -5.1600
Max Act: 4.9413. Min Act: -0.1700
Data Index: 2678540 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1600. Min Range: -5.1600
Max Act: 4.9100. Min Act: -0.1700
Data Index: 892677 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1600. Min Range: -5.1600
Max Act: 4.9413. Min Act: -0.1700
Data Index: 6843136 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #19