Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3525 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9625. Min Range: -6.9625
Max Act: 6.9625. Min Act: -0.1700
Data Index: 4960772 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9625. Min Range: -6.9625
Max Act: 6.9000. Min Act: -0.1700
Data Index: 2228267 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9625. Min Range: -6.9625
Max Act: 6.8375. Min Act: -0.1700
Data Index: 1017846 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9625. Min Range: -6.9625
Max Act: 6.8063. Min Act: -0.1700
Data Index: 889494 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9625. Min Range: -6.9625
Max Act: 6.8063. Min Act: -0.1700
Data Index: 6811800 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9625. Min Range: -6.9625
Max Act: 6.8063. Min Act: -0.1700
Data Index: 8722915 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9625. Min Range: -6.9625
Max Act: 6.7750. Min Act: -0.1700
Data Index: 2463702 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9625. Min Range: -6.9625
Max Act: 6.7438. Min Act: -0.1700
Data Index: 5840081 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9625. Min Range: -6.9625
Max Act: 6.7438. Min Act: -0.1700
Data Index: 2436198 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9625. Min Range: -6.9625
Max Act: 6.6813. Min Act: -0.1700
Data Index: 2180857 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9625. Min Range: -6.9625
Max Act: 6.6500. Min Act: -0.1700
Data Index: 1483175 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9625. Min Range: -6.9625
Max Act: 6.6500. Min Act: -0.1700
Data Index: 5735681 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9625. Min Range: -6.9625
Max Act: 6.6500. Min Act: -0.1700
Data Index: 6616059 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9625. Min Range: -6.9625
Max Act: 6.6500. Min Act: -0.1700
Data Index: 5975363 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9625. Min Range: -6.9625
Max Act: 6.6500. Min Act: -0.1700
Data Index: 7640593 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9625. Min Range: -6.9625
Max Act: 6.6500. Min Act: -0.1700
Data Index: 5010283 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9625. Min Range: -6.9625
Max Act: 6.6188. Min Act: -0.1700
Data Index: 410922 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9625. Min Range: -6.9625
Max Act: 6.6188. Min Act: -0.1700
Data Index: 7843629 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9625. Min Range: -6.9625
Max Act: 6.6188. Min Act: -0.1700
Data Index: 982715 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9625. Min Range: -6.9625
Max Act: 6.5563. Min Act: -0.1700
Data Index: 5974157 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19