Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2669 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7250. Min Range: -5.7250
Max Act: 5.7250. Min Act: -0.1700
Data Index: 2942098 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7250. Min Range: -5.7250
Max Act: 5.6625. Min Act: -0.1700
Data Index: 2878425 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7250. Min Range: -5.7250
Max Act: 5.6000. Min Act: -0.1700
Data Index: 6999707 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7250. Min Range: -5.7250
Max Act: 5.5687. Min Act: -0.1700
Data Index: 57178 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7250. Min Range: -5.7250
Max Act: 5.4437. Min Act: -0.1700
Data Index: 3220582 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7250. Min Range: -5.7250
Max Act: 5.4437. Min Act: -0.1700
Data Index: 2839295 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7250. Min Range: -5.7250
Max Act: 5.4437. Min Act: -0.1700
Data Index: 8550424 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7250. Min Range: -5.7250
Max Act: 5.4125. Min Act: -0.1700
Data Index: 6502887 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7250. Min Range: -5.7250
Max Act: 5.4437. Min Act: -0.1700
Data Index: 8641750 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7250. Min Range: -5.7250
Max Act: 5.3812. Min Act: -0.1700
Data Index: 5920721 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7250. Min Range: -5.7250
Max Act: 5.3812. Min Act: -0.1700
Data Index: 7464330 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7250. Min Range: -5.7250
Max Act: 5.3812. Min Act: -0.1700
Data Index: 2037200 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7250. Min Range: -5.7250
Max Act: 5.3812. Min Act: -0.1700
Data Index: 4047842 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7250. Min Range: -5.7250
Max Act: 5.3187. Min Act: -0.1700
Data Index: 926916 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7250. Min Range: -5.7250
Max Act: 5.3500. Min Act: -0.1700
Data Index: 8113990 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7250. Min Range: -5.7250
Max Act: 5.3187. Min Act: -0.1700
Data Index: 1078985 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7250. Min Range: -5.7250
Max Act: 5.3500. Min Act: -0.1700
Data Index: 8231146 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7250. Min Range: -5.7250
Max Act: 5.3500. Min Act: -0.1700
Data Index: 4303944 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7250. Min Range: -5.7250
Max Act: 5.3500. Min Act: -0.1700
Data Index: 4914176 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7250. Min Range: -5.7250
Max Act: 5.3500. Min Act: -0.1700
Data Index: 3201812 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #19