Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3546 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2763. Min Range: -8.2763
Max Act: 8.2763. Min Act: -0.1700
Data Index: 8597519 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2763. Min Range: -8.2763
Max Act: 8.1513. Min Act: -0.1700
Data Index: 8118800 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2763. Min Range: -8.2763
Max Act: 8.0263. Min Act: -0.1700
Data Index: 1459758 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2763. Min Range: -8.2763
Max Act: 7.9638. Min Act: -0.1700
Data Index: 977960 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2763. Min Range: -8.2763
Max Act: 7.7763. Min Act: -0.1700
Data Index: 2694334 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2763. Min Range: -8.2763
Max Act: 7.7138. Min Act: -0.1700
Data Index: 7472222 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2763. Min Range: -8.2763
Max Act: 7.7138. Min Act: -0.1700
Data Index: 4056075 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2763. Min Range: -8.2763
Max Act: 7.7138. Min Act: -0.1700
Data Index: 5448691 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2763. Min Range: -8.2763
Max Act: 7.7138. Min Act: -0.1700
Data Index: 8246508 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2763. Min Range: -8.2763
Max Act: 7.6826. Min Act: -0.1700
Data Index: 5942750 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2763. Min Range: -8.2763
Max Act: 7.6826. Min Act: -0.1700
Data Index: 2466321 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2763. Min Range: -8.2763
Max Act: 7.6513. Min Act: -0.1700
Data Index: 3404576 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2763. Min Range: -8.2763
Max Act: 7.6513. Min Act: -0.1700
Data Index: 822216 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2763. Min Range: -8.2763
Max Act: 7.6201. Min Act: -0.1700
Data Index: 8070265 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2763. Min Range: -8.2763
Max Act: 7.5576. Min Act: -0.1700
Data Index: 3149853 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2763. Min Range: -8.2763
Max Act: 7.4951. Min Act: -0.1700
Data Index: 8120466 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2763. Min Range: -8.2763
Max Act: 7.4951. Min Act: -0.1700
Data Index: 1809715 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2763. Min Range: -8.2763
Max Act: 7.4951. Min Act: -0.1700
Data Index: 8010860 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2763. Min Range: -8.2763
Max Act: 7.4951. Min Act: -0.1700
Data Index: 5769742 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2763. Min Range: -8.2763
Max Act: 7.4951. Min Act: -0.1700
Data Index: 8046368 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19