Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2995 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8894. Min Range: -7.8894
Max Act: 7.8894. Min Act: -0.1700
Data Index: 2117770 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8894. Min Range: -7.8894
Max Act: 7.7644. Min Act: -0.1700
Data Index: 7585550 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8894. Min Range: -7.8894
Max Act: 7.7644. Min Act: -0.1700
Data Index: 4853844 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8894. Min Range: -7.8894
Max Act: 7.6394. Min Act: -0.1700
Data Index: 7783438 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8894. Min Range: -7.8894
Max Act: 7.6394. Min Act: -0.1700
Data Index: 4197864 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8894. Min Range: -7.8894
Max Act: 7.3894. Min Act: -0.1700
Data Index: 5361732 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8894. Min Range: -7.8894
Max Act: 7.3582. Min Act: -0.1700
Data Index: 5781131 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8894. Min Range: -7.8894
Max Act: 7.3269. Min Act: -0.1700
Data Index: 2195607 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8894. Min Range: -7.8894
Max Act: 7.3269. Min Act: -0.1700
Data Index: 5368032 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8894. Min Range: -7.8894
Max Act: 7.2957. Min Act: -0.1700
Data Index: 4334980 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8894. Min Range: -7.8894
Max Act: 7.2644. Min Act: -0.1700
Data Index: 4815083 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8894. Min Range: -7.8894
Max Act: 7.2957. Min Act: -0.1700
Data Index: 2498431 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8894. Min Range: -7.8894
Max Act: 7.2644. Min Act: -0.1700
Data Index: 7120390 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8894. Min Range: -7.8894
Max Act: 7.2332. Min Act: -0.1700
Data Index: 7184829 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8894. Min Range: -7.8894
Max Act: 7.2332. Min Act: -0.1700
Data Index: 2510852 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8894. Min Range: -7.8894
Max Act: 7.2332. Min Act: -0.1700
Data Index: 2636776 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8894. Min Range: -7.8894
Max Act: 7.2019. Min Act: -0.1700
Data Index: 6601673 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8894. Min Range: -7.8894
Max Act: 7.1707. Min Act: -0.1700
Data Index: 3694964 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8894. Min Range: -7.8894
Max Act: 7.2019. Min Act: -0.1700
Data Index: 3263052 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8894. Min Range: -7.8894
Max Act: 7.1707. Min Act: -0.1700
Data Index: 8671172 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19