Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2864 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9737. Min Range: -10.9737
Max Act: 10.9737. Min Act: -0.1700
Data Index: 894856 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9737. Min Range: -10.9737
Max Act: 10.8487. Min Act: -0.1700
Data Index: 5378629 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9737. Min Range: -10.9737
Max Act: 10.7862. Min Act: -0.1700
Data Index: 7465065 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9737. Min Range: -10.9737
Max Act: 10.6612. Min Act: -0.1700
Data Index: 3176555 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9737. Min Range: -10.9737
Max Act: 10.5987. Min Act: -0.1700
Data Index: 7019864 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9737. Min Range: -10.9737
Max Act: 10.5987. Min Act: -0.1700
Data Index: 5378622 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9737. Min Range: -10.9737
Max Act: 10.4737. Min Act: -0.1700
Data Index: 240407 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9737. Min Range: -10.9737
Max Act: 10.4112. Min Act: -0.1700
Data Index: 879951 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9737. Min Range: -10.9737
Max Act: 10.4737. Min Act: -0.1700
Data Index: 5195718 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9737. Min Range: -10.9737
Max Act: 10.4737. Min Act: -0.1700
Data Index: 5602858 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9737. Min Range: -10.9737
Max Act: 10.4112. Min Act: -0.1700
Data Index: 5845401 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9737. Min Range: -10.9737
Max Act: 10.3487. Min Act: -0.1700
Data Index: 5378616 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9737. Min Range: -10.9737
Max Act: 10.3487. Min Act: -0.1700
Data Index: 3288439 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9737. Min Range: -10.9737
Max Act: 10.2862. Min Act: -0.1700
Data Index: 5378614 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9737. Min Range: -10.9737
Max Act: 10.2237. Min Act: -0.1700
Data Index: 1611320 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9737. Min Range: -10.9737
Max Act: 10.2862. Min Act: -0.1700
Data Index: 5714917 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9737. Min Range: -10.9737
Max Act: 10.2237. Min Act: -0.1700
Data Index: 1556670 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9737. Min Range: -10.9737
Max Act: 10.2237. Min Act: -0.1700
Data Index: 1952864 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9737. Min Range: -10.9737
Max Act: 10.2237. Min Act: -0.1700
Data Index: 1316132 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9737. Min Range: -10.9737
Max Act: 10.2237. Min Act: -0.1700
Data Index: 7636582 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #19