Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 634 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8810. Min Range: -2.8810
Max Act: 2.8810. Min Act: -0.1700
Data Index: 1747427 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8810. Min Range: -2.8810
Max Act: 2.8174. Min Act: -0.1700
Data Index: 5682698 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8810. Min Range: -2.8810
Max Act: 2.8015. Min Act: -0.1700
Data Index: 7283402 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8810. Min Range: -2.8810
Max Act: 2.7856. Min Act: -0.1700
Data Index: 919186 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8810. Min Range: -2.8810
Max Act: 2.7697. Min Act: -0.1700
Data Index: 5612311 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8810. Min Range: -2.8810
Max Act: 2.7377. Min Act: -0.1700
Data Index: 598930 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8810. Min Range: -2.8810
Max Act: 2.7377. Min Act: -0.1700
Data Index: 4376817 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8810. Min Range: -2.8810
Max Act: 2.7218. Min Act: -0.1700
Data Index: 6865037 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8810. Min Range: -2.8810
Max Act: 2.7377. Min Act: -0.1700
Data Index: 2606621 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8810. Min Range: -2.8810
Max Act: 2.7058. Min Act: -0.1700
Data Index: 7116915 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8810. Min Range: -2.8810
Max Act: 2.7218. Min Act: -0.1700
Data Index: 6683277 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8810. Min Range: -2.8810
Max Act: 2.7058. Min Act: -0.1700
Data Index: 1723463 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8810. Min Range: -2.8810
Max Act: 2.7058. Min Act: -0.1700
Data Index: 3824894 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8810. Min Range: -2.8810
Max Act: 2.7058. Min Act: -0.1700
Data Index: 2976971 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8810. Min Range: -2.8810
Max Act: 2.7058. Min Act: -0.1700
Data Index: 7617966 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8810. Min Range: -2.8810
Max Act: 2.6898. Min Act: -0.1700
Data Index: 8640516 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8810. Min Range: -2.8810
Max Act: 2.6898. Min Act: -0.1700
Data Index: 437892 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8810. Min Range: -2.8810
Max Act: 2.6898. Min Act: -0.1700
Data Index: 3722451 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8810. Min Range: -2.8810
Max Act: 2.7058. Min Act: -0.1700
Data Index: 7859534 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8810. Min Range: -2.8810
Max Act: 2.6898. Min Act: -0.1700
Data Index: 7858350 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19