Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3407 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3066. Min Range: -5.3066
Max Act: 5.3066. Min Act: -0.1700
Data Index: 5612453 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3066. Min Range: -5.3066
Max Act: 5.2753. Min Act: -0.1700
Data Index: 2835131 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3066. Min Range: -5.3066
Max Act: 5.0566. Min Act: -0.1700
Data Index: 4703866 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3066. Min Range: -5.3066
Max Act: 5.0253. Min Act: -0.1700
Data Index: 2802328 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3066. Min Range: -5.3066
Max Act: 5.0253. Min Act: -0.1700
Data Index: 2072992 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3066. Min Range: -5.3066
Max Act: 5.0253. Min Act: -0.1700
Data Index: 8245678 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3066. Min Range: -5.3066
Max Act: 4.9628. Min Act: -0.1700
Data Index: 3595581 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3066. Min Range: -5.3066
Max Act: 4.9941. Min Act: -0.1700
Data Index: 5294344 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3066. Min Range: -5.3066
Max Act: 4.9003. Min Act: -0.1700
Data Index: 8627727 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3066. Min Range: -5.3066
Max Act: 4.9316. Min Act: -0.1700
Data Index: 7846835 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3066. Min Range: -5.3066
Max Act: 4.9316. Min Act: -0.1700
Data Index: 8018211 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3066. Min Range: -5.3066
Max Act: 4.9316. Min Act: -0.1700
Data Index: 3930471 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3066. Min Range: -5.3066
Max Act: 4.9003. Min Act: -0.1700
Data Index: 6389589 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3066. Min Range: -5.3066
Max Act: 4.8691. Min Act: -0.1700
Data Index: 6476428 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3066. Min Range: -5.3066
Max Act: 4.8691. Min Act: -0.1700
Data Index: 956411 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3066. Min Range: -5.3066
Max Act: 4.8691. Min Act: -0.1700
Data Index: 6215938 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3066. Min Range: -5.3066
Max Act: 4.8691. Min Act: -0.1700
Data Index: 6208238 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3066. Min Range: -5.3066
Max Act: 4.8691. Min Act: -0.1700
Data Index: 8619696 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3066. Min Range: -5.3066
Max Act: 4.8691. Min Act: -0.1700
Data Index: 7616317 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3066. Min Range: -5.3066
Max Act: 4.8691. Min Act: -0.1700
Data Index: 5627967 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19