Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3585 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7697. Min Range: -3.7697
Max Act: 3.7697. Min Act: -0.1700
Data Index: 7906532 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7697. Min Range: -3.7697
Max Act: 3.4567. Min Act: -0.1700
Data Index: 7569018 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7697. Min Range: -3.7697
Max Act: 3.4410. Min Act: -0.1700
Data Index: 4346469 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7697. Min Range: -3.7697
Max Act: 3.3940. Min Act: -0.1700
Data Index: 874337 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7697. Min Range: -3.7697
Max Act: 3.3783. Min Act: -0.1700
Data Index: 364947 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7697. Min Range: -3.7697
Max Act: 3.3626. Min Act: -0.1700
Data Index: 1798010 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7697. Min Range: -3.7697
Max Act: 3.3626. Min Act: -0.1700
Data Index: 1187564 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7697. Min Range: -3.7697
Max Act: 3.3469. Min Act: -0.1700
Data Index: 3935222 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7697. Min Range: -3.7697
Max Act: 3.3313. Min Act: -0.1700
Data Index: 7325412 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7697. Min Range: -3.7697
Max Act: 3.3156. Min Act: -0.1700
Data Index: 4268835 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7697. Min Range: -3.7697
Max Act: 3.3156. Min Act: -0.1700
Data Index: 1461578 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7697. Min Range: -3.7697
Max Act: 3.3156. Min Act: -0.1700
Data Index: 1709970 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7697. Min Range: -3.7697
Max Act: 3.3156. Min Act: -0.1700
Data Index: 3672401 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7697. Min Range: -3.7697
Max Act: 3.2999. Min Act: -0.1700
Data Index: 8237868 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7697. Min Range: -3.7697
Max Act: 3.2999. Min Act: -0.1700
Data Index: 966166 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7697. Min Range: -3.7697
Max Act: 3.2842. Min Act: -0.1700
Data Index: 5675953 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7697. Min Range: -3.7697
Max Act: 3.2842. Min Act: -0.1700
Data Index: 1044087 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7697. Min Range: -3.7697
Max Act: 3.2842. Min Act: -0.1700
Data Index: 7725494 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7697. Min Range: -3.7697
Max Act: 3.2842. Min Act: -0.1700
Data Index: 6806492 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7697. Min Range: -3.7697
Max Act: 3.2685. Min Act: -0.1700
Data Index: 7964207 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19