Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3524 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6333. Min Range: -7.6333
Max Act: 7.6333. Min Act: -0.1700
Data Index: 4182734 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6333. Min Range: -7.6333
Max Act: 7.3520. Min Act: -0.1700
Data Index: 5494712 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6333. Min Range: -7.6333
Max Act: 7.3208. Min Act: -0.1700
Data Index: 6323131 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6333. Min Range: -7.6333
Max Act: 7.1958. Min Act: -0.1700
Data Index: 2239073 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6333. Min Range: -7.6333
Max Act: 7.1333. Min Act: -0.1700
Data Index: 5818815 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6333. Min Range: -7.6333
Max Act: 7.1020. Min Act: -0.1700
Data Index: 2458630 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6333. Min Range: -7.6333
Max Act: 7.0708. Min Act: -0.1700
Data Index: 30476 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6333. Min Range: -7.6333
Max Act: 7.0708. Min Act: -0.1700
Data Index: 5163160 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6333. Min Range: -7.6333
Max Act: 7.0395. Min Act: -0.1700
Data Index: 1351411 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6333. Min Range: -7.6333
Max Act: 7.0708. Min Act: -0.1700
Data Index: 1362130 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6333. Min Range: -7.6333
Max Act: 7.0395. Min Act: -0.1700
Data Index: 8078922 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6333. Min Range: -7.6333
Max Act: 7.0395. Min Act: -0.1700
Data Index: 4202724 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6333. Min Range: -7.6333
Max Act: 7.0083. Min Act: -0.1700
Data Index: 1418950 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6333. Min Range: -7.6333
Max Act: 7.0083. Min Act: -0.1700
Data Index: 1074705 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6333. Min Range: -7.6333
Max Act: 6.9770. Min Act: -0.1700
Data Index: 1440974 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6333. Min Range: -7.6333
Max Act: 6.9770. Min Act: -0.1700
Data Index: 5205125 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6333. Min Range: -7.6333
Max Act: 6.9770. Min Act: -0.1700
Data Index: 5528608 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6333. Min Range: -7.6333
Max Act: 6.9770. Min Act: -0.1700
Data Index: 863014 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6333. Min Range: -7.6333
Max Act: 6.9145. Min Act: -0.1700
Data Index: 3795929 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6333. Min Range: -7.6333
Max Act: 6.9145. Min Act: -0.1700
Data Index: 6300830 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19