Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3441 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3863. Min Range: -7.3863
Max Act: 7.3863. Min Act: -0.1700
Data Index: 2047444 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3863. Min Range: -7.3863
Max Act: 6.8551. Min Act: -0.1700
Data Index: 3175060 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3863. Min Range: -7.3863
Max Act: 6.8551. Min Act: -0.1700
Data Index: 2673671 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3863. Min Range: -7.3863
Max Act: 6.8238. Min Act: -0.1700
Data Index: 2726874 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3863. Min Range: -7.3863
Max Act: 6.7926. Min Act: -0.1700
Data Index: 8657738 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3863. Min Range: -7.3863
Max Act: 6.6988. Min Act: -0.1700
Data Index: 4453638 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3863. Min Range: -7.3863
Max Act: 6.6051. Min Act: -0.1700
Data Index: 5321808 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3863. Min Range: -7.3863
Max Act: 6.6051. Min Act: -0.1700
Data Index: 6409734 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3863. Min Range: -7.3863
Max Act: 6.6051. Min Act: -0.1700
Data Index: 1616387 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3863. Min Range: -7.3863
Max Act: 6.5738. Min Act: -0.1700
Data Index: 1410426 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3863. Min Range: -7.3863
Max Act: 6.5426. Min Act: -0.1700
Data Index: 1838609 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3863. Min Range: -7.3863
Max Act: 6.5113. Min Act: -0.1700
Data Index: 4468104 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3863. Min Range: -7.3863
Max Act: 6.5113. Min Act: -0.1700
Data Index: 2576472 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3863. Min Range: -7.3863
Max Act: 6.4801. Min Act: -0.1700
Data Index: 1665587 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3863. Min Range: -7.3863
Max Act: 6.4801. Min Act: -0.1700
Data Index: 5974892 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3863. Min Range: -7.3863
Max Act: 6.4488. Min Act: -0.1700
Data Index: 2054216 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3863. Min Range: -7.3863
Max Act: 6.5113. Min Act: -0.1700
Data Index: 5959987 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3863. Min Range: -7.3863
Max Act: 6.4801. Min Act: -0.1700
Data Index: 2365559 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3863. Min Range: -7.3863
Max Act: 6.4488. Min Act: -0.1700
Data Index: 5089149 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3863. Min Range: -7.3863
Max Act: 6.4801. Min Act: -0.1700
Data Index: 5177294 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #19