Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3313 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1756. Min Range: -10.1756
Max Act: 10.1756. Min Act: -0.1700
Data Index: 4709630 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1756. Min Range: -10.1756
Max Act: 9.9256. Min Act: -0.1700
Data Index: 7410380 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1756. Min Range: -10.1756
Max Act: 9.5506. Min Act: -0.1700
Data Index: 1802707 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1756. Min Range: -10.1756
Max Act: 9.4881. Min Act: -0.1700
Data Index: 8422724 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1756. Min Range: -10.1756
Max Act: 9.4256. Min Act: -0.1700
Data Index: 4709629 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1756. Min Range: -10.1756
Max Act: 9.4256. Min Act: -0.1700
Data Index: 7410378 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1756. Min Range: -10.1756
Max Act: 9.1756. Min Act: -0.1700
Data Index: 335138 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1756. Min Range: -10.1756
Max Act: 9.1131. Min Act: -0.1700
Data Index: 8422722 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1756. Min Range: -10.1756
Max Act: 8.9881. Min Act: -0.1700
Data Index: 2237890 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1756. Min Range: -10.1756
Max Act: 8.7381. Min Act: -0.1700
Data Index: 5685443 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1756. Min Range: -10.1756
Max Act: 8.6756. Min Act: -0.1700
Data Index: 3557076 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1756. Min Range: -10.1756
Max Act: 8.6131. Min Act: -0.1700
Data Index: 7692192 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1756. Min Range: -10.1756
Max Act: 8.6131. Min Act: -0.1700
Data Index: 7173768 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1756. Min Range: -10.1756
Max Act: 8.4881. Min Act: -0.1700
Data Index: 593552 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1756. Min Range: -10.1756
Max Act: 8.4881. Min Act: -0.1700
Data Index: 4462714 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1756. Min Range: -10.1756
Max Act: 8.4881. Min Act: -0.1700
Data Index: 4951729 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1756. Min Range: -10.1756
Max Act: 8.4256. Min Act: -0.1700
Data Index: 4709628 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1756. Min Range: -10.1756
Max Act: 8.4256. Min Act: -0.1700
Data Index: 7374332 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1756. Min Range: -10.1756
Max Act: 8.3631. Min Act: -0.1700
Data Index: 6011462 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1756. Min Range: -10.1756
Max Act: 8.3631. Min Act: -0.1700
Data Index: 5943480 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #19