Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3437 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2785. Min Range: -8.2785
Max Act: 8.2785. Min Act: -0.1700
Data Index: 843843 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2785. Min Range: -8.2785
Max Act: 8.1535. Min Act: -0.1700
Data Index: 8724214 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2785. Min Range: -8.2785
Max Act: 8.1535. Min Act: -0.1700
Data Index: 3026024 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2785. Min Range: -8.2785
Max Act: 8.1535. Min Act: -0.1700
Data Index: 2577007 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2785. Min Range: -8.2785
Max Act: 8.0910. Min Act: -0.1700
Data Index: 5954124 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2785. Min Range: -8.2785
Max Act: 8.0910. Min Act: -0.1700
Data Index: 7488967 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2785. Min Range: -8.2785
Max Act: 8.0285. Min Act: -0.1700
Data Index: 686969 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2785. Min Range: -8.2785
Max Act: 8.0285. Min Act: -0.1700
Data Index: 6892223 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2785. Min Range: -8.2785
Max Act: 7.9660. Min Act: -0.1700
Data Index: 8775423 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2785. Min Range: -8.2785
Max Act: 7.9660. Min Act: -0.1700
Data Index: 7855176 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2785. Min Range: -8.2785
Max Act: 7.9660. Min Act: -0.1700
Data Index: 217181 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2785. Min Range: -8.2785
Max Act: 7.9660. Min Act: -0.1700
Data Index: 3323254 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2785. Min Range: -8.2785
Max Act: 7.9035. Min Act: -0.1700
Data Index: 5996869 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2785. Min Range: -8.2785
Max Act: 7.9035. Min Act: -0.1700
Data Index: 8715659 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2785. Min Range: -8.2785
Max Act: 7.9035. Min Act: -0.1700
Data Index: 936546 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2785. Min Range: -8.2785
Max Act: 7.9035. Min Act: -0.1700
Data Index: 1195270 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2785. Min Range: -8.2785
Max Act: 7.8410. Min Act: -0.1700
Data Index: 836099 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2785. Min Range: -8.2785
Max Act: 7.7785. Min Act: -0.1700
Data Index: 4988244 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2785. Min Range: -8.2785
Max Act: 7.7785. Min Act: -0.1700
Data Index: 6206847 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2785. Min Range: -8.2785
Max Act: 7.7785. Min Act: -0.1700
Data Index: 3625508 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19