Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2976 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0576. Min Range: -5.0576
Max Act: 5.0576. Min Act: -0.1700
Data Index: 8653806 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0576. Min Range: -5.0576
Max Act: 5.0264. Min Act: -0.1700
Data Index: 8653807 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0576. Min Range: -5.0576
Max Act: 4.9951. Min Act: -0.1700
Data Index: 1527118 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0576. Min Range: -5.0576
Max Act: 4.9014. Min Act: -0.1700
Data Index: 1527126 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0576. Min Range: -5.0576
Max Act: 4.8701. Min Act: -0.1700
Data Index: 2262212 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0576. Min Range: -5.0576
Max Act: 4.9014. Min Act: -0.1700
Data Index: 684669 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0576. Min Range: -5.0576
Max Act: 4.8389. Min Act: -0.1700
Data Index: 6341345 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0576. Min Range: -5.0576
Max Act: 4.8701. Min Act: -0.1700
Data Index: 4415497 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0576. Min Range: -5.0576
Max Act: 4.8701. Min Act: -0.1700
Data Index: 2984077 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0576. Min Range: -5.0576
Max Act: 4.8701. Min Act: -0.1700
Data Index: 8731694 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0576. Min Range: -5.0576
Max Act: 4.8389. Min Act: -0.1700
Data Index: 5663260 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0576. Min Range: -5.0576
Max Act: 4.8389. Min Act: -0.1700
Data Index: 7443373 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0576. Min Range: -5.0576
Max Act: 4.8389. Min Act: -0.1700
Data Index: 4735607 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0576. Min Range: -5.0576
Max Act: 4.8076. Min Act: -0.1700
Data Index: 7757171 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0576. Min Range: -5.0576
Max Act: 4.8076. Min Act: -0.1700
Data Index: 4415033 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0576. Min Range: -5.0576
Max Act: 4.8076. Min Act: -0.1700
Data Index: 4048284 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0576. Min Range: -5.0576
Max Act: 4.7764. Min Act: -0.1700
Data Index: 4415484 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0576. Min Range: -5.0576
Max Act: 4.7764. Min Act: -0.1700
Data Index: 2266840 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0576. Min Range: -5.0576
Max Act: 4.7451. Min Act: -0.1700
Data Index: 4837423 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0576. Min Range: -5.0576
Max Act: 4.7451. Min Act: -0.1700
Data Index: 3632714 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #19