Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5352 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1759. Min Range: -6.1759
Max Act: 6.1759. Min Act: -0.1700
Data Index: 3604972 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1759. Min Range: -6.1759
Max Act: 6.0821. Min Act: -0.1700
Data Index: 2246029 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1759. Min Range: -6.1759
Max Act: 6.0196. Min Act: -0.1700
Data Index: 2246026 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1759. Min Range: -6.1759
Max Act: 5.8946. Min Act: -0.1700
Data Index: 7087532 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1759. Min Range: -6.1759
Max Act: 5.8634. Min Act: -0.1700
Data Index: 6648672 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1759. Min Range: -6.1759
Max Act: 5.8634. Min Act: -0.1700
Data Index: 7087539 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1759. Min Range: -6.1759
Max Act: 5.8321. Min Act: -0.1700
Data Index: 8653823 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1759. Min Range: -6.1759
Max Act: 5.8321. Min Act: -0.1700
Data Index: 7087528 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1759. Min Range: -6.1759
Max Act: 5.8009. Min Act: -0.1700
Data Index: 8653815 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1759. Min Range: -6.1759
Max Act: 5.8009. Min Act: -0.1700
Data Index: 7087529 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1759. Min Range: -6.1759
Max Act: 5.8009. Min Act: -0.1700
Data Index: 6648653 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1759. Min Range: -6.1759
Max Act: 5.7696. Min Act: -0.1700
Data Index: 4015105 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1759. Min Range: -6.1759
Max Act: 5.7384. Min Act: -0.1700
Data Index: 2215185 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1759. Min Range: -6.1759
Max Act: 5.7696. Min Act: -0.1700
Data Index: 5704801 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1759. Min Range: -6.1759
Max Act: 5.7696. Min Act: -0.1700
Data Index: 2215193 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1759. Min Range: -6.1759
Max Act: 5.7384. Min Act: -0.1700
Data Index: 3108589 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1759. Min Range: -6.1759
Max Act: 5.7384. Min Act: -0.1700
Data Index: 6648664 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1759. Min Range: -6.1759
Max Act: 5.7384. Min Act: -0.1700
Data Index: 4015117 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1759. Min Range: -6.1759
Max Act: 5.7071. Min Act: -0.1700
Data Index: 3108578 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1759. Min Range: -6.1759
Max Act: 5.7384. Min Act: -0.1700
Data Index: 3108580 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19