Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3815 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3000. Min Range: -6.3000
Max Act: 6.3000. Min Act: -0.1700
Data Index: 4793220 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3000. Min Range: -6.3000
Max Act: 5.9250. Min Act: -0.1700
Data Index: 6521567 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3000. Min Range: -6.3000
Max Act: 5.9563. Min Act: -0.1700
Data Index: 3293179 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3000. Min Range: -6.3000
Max Act: 5.9250. Min Act: -0.1700
Data Index: 4046008 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3000. Min Range: -6.3000
Max Act: 5.8000. Min Act: -0.1700
Data Index: 4854543 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3000. Min Range: -6.3000
Max Act: 5.8313. Min Act: -0.1700
Data Index: 4499988 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3000. Min Range: -6.3000
Max Act: 5.7688. Min Act: -0.1700
Data Index: 2570532 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3000. Min Range: -6.3000
Max Act: 5.8000. Min Act: -0.1700
Data Index: 3256116 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3000. Min Range: -6.3000
Max Act: 5.7375. Min Act: -0.1700
Data Index: 3704312 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3000. Min Range: -6.3000
Max Act: 5.7063. Min Act: -0.1700
Data Index: 1269875 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3000. Min Range: -6.3000
Max Act: 5.7063. Min Act: -0.1700
Data Index: 6632526 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3000. Min Range: -6.3000
Max Act: 5.6750. Min Act: -0.1700
Data Index: 6653654 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3000. Min Range: -6.3000
Max Act: 5.6750. Min Act: -0.1700
Data Index: 607924 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3000. Min Range: -6.3000
Max Act: 5.6438. Min Act: -0.1700
Data Index: 922302 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3000. Min Range: -6.3000
Max Act: 5.6750. Min Act: -0.1700
Data Index: 301482 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3000. Min Range: -6.3000
Max Act: 5.6125. Min Act: -0.1700
Data Index: 6031728 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3000. Min Range: -6.3000
Max Act: 5.6125. Min Act: -0.1700
Data Index: 6144521 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3000. Min Range: -6.3000
Max Act: 5.6125. Min Act: -0.1700
Data Index: 4104567 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3000. Min Range: -6.3000
Max Act: 5.6438. Min Act: -0.1700
Data Index: 2628764 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3000. Min Range: -6.3000
Max Act: 5.6125. Min Act: -0.1700
Data Index: 5498604 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19