Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3005 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7338. Min Range: -5.7338
Max Act: 5.6713. Min Act: -0.1700
Data Index: 8685880 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7338. Min Range: -5.7338
Max Act: 5.7338. Min Act: -0.1700
Data Index: 3968080 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7338. Min Range: -5.7338
Max Act: 5.7025. Min Act: -0.1700
Data Index: 1358571 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7338. Min Range: -5.7338
Max Act: 5.6713. Min Act: -0.1700
Data Index: 2137724 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7338. Min Range: -5.7338
Max Act: 5.6713. Min Act: -0.1700
Data Index: 248580 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7338. Min Range: -5.7338
Max Act: 5.6088. Min Act: -0.1697
Data Index: 1924652 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7338. Min Range: -5.7338
Max Act: 5.6088. Min Act: -0.1700
Data Index: 5872046 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7338. Min Range: -5.7338
Max Act: 5.6400. Min Act: -0.1700
Data Index: 2803986 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7338. Min Range: -5.7338
Max Act: 5.6088. Min Act: -0.1700
Data Index: 6363113 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7338. Min Range: -5.7338
Max Act: 5.6088. Min Act: -0.1700
Data Index: 5815393 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7338. Min Range: -5.7338
Max Act: 5.5775. Min Act: -0.1699
Data Index: 756558 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7338. Min Range: -5.7338
Max Act: 5.6088. Min Act: -0.1700
Data Index: 847801 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7338. Min Range: -5.7338
Max Act: 5.5775. Min Act: -0.1700
Data Index: 5387294 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7338. Min Range: -5.7338
Max Act: 5.6088. Min Act: -0.1700
Data Index: 7446531 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7338. Min Range: -5.7338
Max Act: 5.5775. Min Act: -0.1699
Data Index: 2047541 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7338. Min Range: -5.7338
Max Act: 5.6088. Min Act: -0.1700
Data Index: 6275939 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7338. Min Range: -5.7338
Max Act: 5.5775. Min Act: -0.1700
Data Index: 6806492 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7338. Min Range: -5.7338
Max Act: 5.5150. Min Act: -0.1700
Data Index: 2761076 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7338. Min Range: -5.7338
Max Act: 5.5463. Min Act: -0.1700
Data Index: 3660884 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7338. Min Range: -5.7338
Max Act: 5.5150. Min Act: -0.1699
Data Index: 5456259 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #19