Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2642 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2902. Min Range: -6.2902
Max Act: 6.2902. Min Act: -0.1700
Data Index: 8199227 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2902. Min Range: -6.2902
Max Act: 6.2902. Min Act: -0.1700
Data Index: 7871976 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2902. Min Range: -6.2902
Max Act: 6.1964. Min Act: -0.1700
Data Index: 4348742 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2902. Min Range: -6.2902
Max Act: 6.1652. Min Act: -0.1700
Data Index: 5527690 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2902. Min Range: -6.2902
Max Act: 6.1027. Min Act: -0.1700
Data Index: 6015224 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2902. Min Range: -6.2902
Max Act: 6.0714. Min Act: -0.1700
Data Index: 3957203 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2902. Min Range: -6.2902
Max Act: 6.0714. Min Act: -0.1700
Data Index: 7245270 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2902. Min Range: -6.2902
Max Act: 6.0402. Min Act: -0.1700
Data Index: 3650773 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2902. Min Range: -6.2902
Max Act: 6.0089. Min Act: -0.1700
Data Index: 922996 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2902. Min Range: -6.2902
Max Act: 5.9464. Min Act: -0.1700
Data Index: 3778349 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2902. Min Range: -6.2902
Max Act: 5.9464. Min Act: -0.1700
Data Index: 6944549 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2902. Min Range: -6.2902
Max Act: 5.9464. Min Act: -0.1700
Data Index: 1944677 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2902. Min Range: -6.2902
Max Act: 5.9464. Min Act: -0.1700
Data Index: 2759101 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2902. Min Range: -6.2902
Max Act: 5.9464. Min Act: -0.1700
Data Index: 3650776 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2902. Min Range: -6.2902
Max Act: 5.9152. Min Act: -0.1700
Data Index: 3957201 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2902. Min Range: -6.2902
Max Act: 5.9152. Min Act: -0.1700
Data Index: 8278346 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2902. Min Range: -6.2902
Max Act: 5.9152. Min Act: -0.1700
Data Index: 5560889 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2902. Min Range: -6.2902
Max Act: 5.9152. Min Act: -0.1700
Data Index: 5144053 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2902. Min Range: -6.2902
Max Act: 5.9152. Min Act: -0.1700
Data Index: 400100 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2902. Min Range: -6.2902
Max Act: 5.8839. Min Act: -0.1700
Data Index: 4664132 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19