Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1595 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7631. Min Range: -8.7631
Max Act: 8.7631. Min Act: -0.1700
Data Index: 8792903 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7631. Min Range: -8.7631
Max Act: 8.7006. Min Act: -0.1700
Data Index: 7947942 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7631. Min Range: -8.7631
Max Act: 8.5131. Min Act: -0.1700
Data Index: 3862389 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7631. Min Range: -8.7631
Max Act: 8.4506. Min Act: -0.1700
Data Index: 1479523 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7631. Min Range: -8.7631
Max Act: 8.3881. Min Act: -0.1700
Data Index: 7283802 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7631. Min Range: -8.7631
Max Act: 8.3256. Min Act: -0.1700
Data Index: 6699856 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7631. Min Range: -8.7631
Max Act: 8.3256. Min Act: -0.1700
Data Index: 7792079 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7631. Min Range: -8.7631
Max Act: 8.2631. Min Act: -0.1700
Data Index: 8725016 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7631. Min Range: -8.7631
Max Act: 8.2006. Min Act: -0.1700
Data Index: 6923752 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7631. Min Range: -8.7631
Max Act: 8.2006. Min Act: -0.1700
Data Index: 6136310 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7631. Min Range: -8.7631
Max Act: 8.1381. Min Act: -0.1700
Data Index: 7274020 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7631. Min Range: -8.7631
Max Act: 8.1381. Min Act: -0.1700
Data Index: 7283801 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7631. Min Range: -8.7631
Max Act: 8.0756. Min Act: -0.1700
Data Index: 2649980 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7631. Min Range: -8.7631
Max Act: 8.0131. Min Act: -0.1700
Data Index: 4351341 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7631. Min Range: -8.7631
Max Act: 7.9506. Min Act: -0.1700
Data Index: 3209903 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7631. Min Range: -8.7631
Max Act: 7.9818. Min Act: -0.1700
Data Index: 2545902 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7631. Min Range: -8.7631
Max Act: 7.9818. Min Act: -0.1700
Data Index: 3745513 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7631. Min Range: -8.7631
Max Act: 7.9506. Min Act: -0.1700
Data Index: 109854 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7631. Min Range: -8.7631
Max Act: 7.9506. Min Act: -0.1700
Data Index: 6655156 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7631. Min Range: -8.7631
Max Act: 7.8568. Min Act: -0.1700
Data Index: 1268455 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #19