Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4771 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8420. Min Range: -5.8420
Max Act: 5.8420. Min Act: -0.1700
Data Index: 952678 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8420. Min Range: -5.8420
Max Act: 5.7483. Min Act: -0.1700
Data Index: 2495411 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8420. Min Range: -5.8420
Max Act: 5.7170. Min Act: -0.1700
Data Index: 3074240 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8420. Min Range: -5.8420
Max Act: 5.7483. Min Act: -0.1700
Data Index: 785890 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8420. Min Range: -5.8420
Max Act: 5.6858. Min Act: -0.1700
Data Index: 1938982 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8420. Min Range: -5.8420
Max Act: 5.6858. Min Act: -0.1700
Data Index: 1130371 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8420. Min Range: -5.8420
Max Act: 5.6233. Min Act: -0.1700
Data Index: 8149152 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8420. Min Range: -5.8420
Max Act: 5.5608. Min Act: -0.1700
Data Index: 4038218 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8420. Min Range: -5.8420
Max Act: 5.5608. Min Act: -0.1700
Data Index: 4801714 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8420. Min Range: -5.8420
Max Act: 5.5920. Min Act: -0.1700
Data Index: 8177358 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8420. Min Range: -5.8420
Max Act: 5.5608. Min Act: -0.1700
Data Index: 2924577 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8420. Min Range: -5.8420
Max Act: 5.5295. Min Act: -0.1700
Data Index: 7687156 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8420. Min Range: -5.8420
Max Act: 5.5608. Min Act: -0.1700
Data Index: 558458 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8420. Min Range: -5.8420
Max Act: 5.5608. Min Act: -0.1700
Data Index: 8010845 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8420. Min Range: -5.8420
Max Act: 5.5295. Min Act: -0.1700
Data Index: 2571789 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8420. Min Range: -5.8420
Max Act: 5.5295. Min Act: -0.1700
Data Index: 1508217 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8420. Min Range: -5.8420
Max Act: 5.5295. Min Act: -0.1700
Data Index: 3644756 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8420. Min Range: -5.8420
Max Act: 5.5295. Min Act: -0.1700
Data Index: 7813830 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8420. Min Range: -5.8420
Max Act: 5.4983. Min Act: -0.1700
Data Index: 3468829 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8420. Min Range: -5.8420
Max Act: 5.4670. Min Act: -0.1700
Data Index: 7143686 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #19