Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4807 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6785. Min Range: -6.6785
Max Act: 6.6785. Min Act: -0.1700
Data Index: 7648828 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6785. Min Range: -6.6785
Max Act: 6.6785. Min Act: -0.1700
Data Index: 8213376 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6785. Min Range: -6.6785
Max Act: 6.4598. Min Act: -0.1700
Data Index: 1893914 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6785. Min Range: -6.6785
Max Act: 6.4598. Min Act: -0.1700
Data Index: 451903 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6785. Min Range: -6.6785
Max Act: 6.2410. Min Act: -0.1700
Data Index: 3162248 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6785. Min Range: -6.6785
Max Act: 6.2410. Min Act: -0.1700
Data Index: 6553039 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6785. Min Range: -6.6785
Max Act: 6.2723. Min Act: -0.1700
Data Index: 4000592 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6785. Min Range: -6.6785
Max Act: 6.2410. Min Act: -0.1700
Data Index: 4997724 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6785. Min Range: -6.6785
Max Act: 6.1785. Min Act: -0.1700
Data Index: 4987387 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6785. Min Range: -6.6785
Max Act: 6.1785. Min Act: -0.1700
Data Index: 8655753 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6785. Min Range: -6.6785
Max Act: 6.2098. Min Act: -0.1700
Data Index: 3198045 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6785. Min Range: -6.6785
Max Act: 6.1160. Min Act: -0.1700
Data Index: 5816683 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6785. Min Range: -6.6785
Max Act: 6.1473. Min Act: -0.1700
Data Index: 3818309 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6785. Min Range: -6.6785
Max Act: 6.1473. Min Act: -0.1700
Data Index: 4860833 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6785. Min Range: -6.6785
Max Act: 6.1473. Min Act: -0.1700
Data Index: 5856179 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6785. Min Range: -6.6785
Max Act: 6.1785. Min Act: -0.1700
Data Index: 2792354 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6785. Min Range: -6.6785
Max Act: 6.1473. Min Act: -0.1700
Data Index: 936412 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6785. Min Range: -6.6785
Max Act: 6.1160. Min Act: -0.1700
Data Index: 8370013 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6785. Min Range: -6.6785
Max Act: 6.1785. Min Act: -0.1700
Data Index: 1182460 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6785. Min Range: -6.6785
Max Act: 6.1473. Min Act: -0.1700
Data Index: 6722361 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #19