Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1583 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7875. Min Range: -8.7875
Max Act: 8.7875. Min Act: -0.1700
Data Index: 8314775 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7875. Min Range: -8.7875
Max Act: 8.1937. Min Act: -0.1700
Data Index: 1520400 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7875. Min Range: -8.7875
Max Act: 8.1312. Min Act: -0.1700
Data Index: 8794305 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7875. Min Range: -8.7875
Max Act: 8.0687. Min Act: -0.1700
Data Index: 2873862 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7875. Min Range: -8.7875
Max Act: 8.0375. Min Act: -0.1700
Data Index: 4526698 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7875. Min Range: -8.7875
Max Act: 8.0062. Min Act: -0.1700
Data Index: 6553378 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7875. Min Range: -8.7875
Max Act: 7.9750. Min Act: -0.1700
Data Index: 5825112 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7875. Min Range: -8.7875
Max Act: 7.9437. Min Act: -0.1700
Data Index: 2025621 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7875. Min Range: -8.7875
Max Act: 7.9437. Min Act: -0.1700
Data Index: 7468163 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7875. Min Range: -8.7875
Max Act: 7.8812. Min Act: -0.1700
Data Index: 6408519 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7875. Min Range: -8.7875
Max Act: 7.8500. Min Act: -0.1700
Data Index: 7027614 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7875. Min Range: -8.7875
Max Act: 7.8187. Min Act: -0.1700
Data Index: 4525082 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7875. Min Range: -8.7875
Max Act: 7.7875. Min Act: -0.1700
Data Index: 7496403 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7875. Min Range: -8.7875
Max Act: 7.7875. Min Act: -0.1700
Data Index: 4795437 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7875. Min Range: -8.7875
Max Act: 7.7562. Min Act: -0.1700
Data Index: 6303295 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7875. Min Range: -8.7875
Max Act: 7.7250. Min Act: -0.1700
Data Index: 2977104 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7875. Min Range: -8.7875
Max Act: 7.6937. Min Act: -0.1700
Data Index: 1349130 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7875. Min Range: -8.7875
Max Act: 7.6937. Min Act: -0.1700
Data Index: 3145399 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7875. Min Range: -8.7875
Max Act: 7.6937. Min Act: -0.1700
Data Index: 1371828 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7875. Min Range: -8.7875
Max Act: 7.6625. Min Act: -0.1700
Data Index: 7907411 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #19