Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4059 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3519. Min Range: -7.3519
Max Act: 7.3519. Min Act: -0.1700
Data Index: 8640467 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3519. Min Range: -7.3519
Max Act: 7.3207. Min Act: -0.1700
Data Index: 3057199 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3519. Min Range: -7.3519
Max Act: 7.3519. Min Act: -0.1700
Data Index: 3384787 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3519. Min Range: -7.3519
Max Act: 7.2269. Min Act: -0.1700
Data Index: 7930107 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3519. Min Range: -7.3519
Max Act: 7.1957. Min Act: -0.1700
Data Index: 2029853 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3519. Min Range: -7.3519
Max Act: 7.1957. Min Act: -0.1700
Data Index: 2434080 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3519. Min Range: -7.3519
Max Act: 7.1957. Min Act: -0.1700
Data Index: 1626679 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3519. Min Range: -7.3519
Max Act: 7.1644. Min Act: -0.1700
Data Index: 4132341 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3519. Min Range: -7.3519
Max Act: 7.1644. Min Act: -0.1700
Data Index: 5095607 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3519. Min Range: -7.3519
Max Act: 7.1644. Min Act: -0.1700
Data Index: 8235493 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3519. Min Range: -7.3519
Max Act: 7.1644. Min Act: -0.1700
Data Index: 1089035 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3519. Min Range: -7.3519
Max Act: 7.1957. Min Act: -0.1700
Data Index: 1626701 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3519. Min Range: -7.3519
Max Act: 7.1332. Min Act: -0.1700
Data Index: 2434082 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3519. Min Range: -7.3519
Max Act: 7.1332. Min Act: -0.1700
Data Index: 2434081 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3519. Min Range: -7.3519
Max Act: 7.1019. Min Act: -0.1700
Data Index: 4883197 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3519. Min Range: -7.3519
Max Act: 7.1019. Min Act: -0.1700
Data Index: 606034 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3519. Min Range: -7.3519
Max Act: 7.0707. Min Act: -0.1700
Data Index: 3660158 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3519. Min Range: -7.3519
Max Act: 7.0707. Min Act: -0.1700
Data Index: 2029859 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3519. Min Range: -7.3519
Max Act: 7.0394. Min Act: -0.1700
Data Index: 8640472 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3519. Min Range: -7.3519
Max Act: 7.0394. Min Act: -0.1700
Data Index: 8640468 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #19