Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3149 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0665. Min Range: -6.0665
Max Act: 6.0665. Min Act: -0.1700
Data Index: 7878211 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0665. Min Range: -6.0665
Max Act: 6.0352. Min Act: -0.1700
Data Index: 392552 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0665. Min Range: -6.0665
Max Act: 5.9102. Min Act: -0.1700
Data Index: 2603867 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0665. Min Range: -6.0665
Max Act: 5.6290. Min Act: -0.1700
Data Index: 5111945 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0665. Min Range: -6.0665
Max Act: 5.6290. Min Act: -0.1700
Data Index: 7084178 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0665. Min Range: -6.0665
Max Act: 5.5665. Min Act: -0.1700
Data Index: 3461790 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0665. Min Range: -6.0665
Max Act: 5.5352. Min Act: -0.1700
Data Index: 351583 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0665. Min Range: -6.0665
Max Act: 5.5040. Min Act: -0.1700
Data Index: 5388068 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0665. Min Range: -6.0665
Max Act: 5.5040. Min Act: -0.1700
Data Index: 6273794 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0665. Min Range: -6.0665
Max Act: 5.4727. Min Act: -0.1700
Data Index: 5884751 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0665. Min Range: -6.0665
Max Act: 5.4727. Min Act: -0.1700
Data Index: 4031700 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0665. Min Range: -6.0665
Max Act: 5.4727. Min Act: -0.1700
Data Index: 557957 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0665. Min Range: -6.0665
Max Act: 5.4727. Min Act: -0.1700
Data Index: 4472052 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0665. Min Range: -6.0665
Max Act: 5.4415. Min Act: -0.1700
Data Index: 3002949 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0665. Min Range: -6.0665
Max Act: 5.4415. Min Act: -0.1700
Data Index: 1957731 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0665. Min Range: -6.0665
Max Act: 5.4102. Min Act: -0.1700
Data Index: 6847909 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0665. Min Range: -6.0665
Max Act: 5.4102. Min Act: -0.1700
Data Index: 5609604 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0665. Min Range: -6.0665
Max Act: 5.3477. Min Act: -0.1700
Data Index: 1181601 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0665. Min Range: -6.0665
Max Act: 5.3790. Min Act: -0.1700
Data Index: 2883161 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0665. Min Range: -6.0665
Max Act: 5.3790. Min Act: -0.1700
Data Index: 7078506 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #19