Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4485 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9419. Min Range: -8.9419
Max Act: 8.9419. Min Act: -0.1700
Data Index: 1650026 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9419. Min Range: -8.9419
Max Act: 8.8794. Min Act: -0.1700
Data Index: 7068447 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9419. Min Range: -8.9419
Max Act: 8.8169. Min Act: -0.1700
Data Index: 6959115 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9419. Min Range: -8.9419
Max Act: 8.6294. Min Act: -0.1700
Data Index: 3749010 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9419. Min Range: -8.9419
Max Act: 8.4419. Min Act: -0.1700
Data Index: 5858559 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9419. Min Range: -8.9419
Max Act: 8.3794. Min Act: -0.1700
Data Index: 2586275 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9419. Min Range: -8.9419
Max Act: 8.3794. Min Act: -0.1700
Data Index: 833832 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9419. Min Range: -8.9419
Max Act: 8.2544. Min Act: -0.1700
Data Index: 5703513 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9419. Min Range: -8.9419
Max Act: 8.1919. Min Act: -0.1700
Data Index: 4892466 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9419. Min Range: -8.9419
Max Act: 8.1919. Min Act: -0.1700
Data Index: 7610270 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9419. Min Range: -8.9419
Max Act: 8.1919. Min Act: -0.1700
Data Index: 2943338 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9419. Min Range: -8.9419
Max Act: 8.1294. Min Act: -0.1700
Data Index: 8052131 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9419. Min Range: -8.9419
Max Act: 8.1294. Min Act: -0.1700
Data Index: 532884 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9419. Min Range: -8.9419
Max Act: 8.1294. Min Act: -0.1700
Data Index: 1191648 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9419. Min Range: -8.9419
Max Act: 8.0669. Min Act: -0.1700
Data Index: 6167686 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9419. Min Range: -8.9419
Max Act: 8.0669. Min Act: -0.1700
Data Index: 1169390 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9419. Min Range: -8.9419
Max Act: 8.0669. Min Act: -0.1700
Data Index: 1266794 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9419. Min Range: -8.9419
Max Act: 8.0669. Min Act: -0.1700
Data Index: 4116998 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9419. Min Range: -8.9419
Max Act: 8.0669. Min Act: -0.1700
Data Index: 4555669 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9419. Min Range: -8.9419
Max Act: 8.0669. Min Act: -0.1700
Data Index: 111741 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #19