Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4012 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1856. Min Range: -9.1856
Max Act: 9.1856. Min Act: -0.1700
Data Index: 6522624 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1856. Min Range: -9.1856
Max Act: 9.0606. Min Act: -0.1700
Data Index: 7741539 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1856. Min Range: -9.1856
Max Act: 8.9981. Min Act: -0.1700
Data Index: 8646427 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1856. Min Range: -9.1856
Max Act: 8.9356. Min Act: -0.1700
Data Index: 1451431 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1856. Min Range: -9.1856
Max Act: 8.8106. Min Act: -0.1700
Data Index: 7061412 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1856. Min Range: -9.1856
Max Act: 8.7481. Min Act: -0.1700
Data Index: 3529226 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1856. Min Range: -9.1856
Max Act: 8.7481. Min Act: -0.1700
Data Index: 1130452 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1856. Min Range: -9.1856
Max Act: 8.7481. Min Act: -0.1700
Data Index: 1941922 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1856. Min Range: -9.1856
Max Act: 8.6856. Min Act: -0.1700
Data Index: 6780923 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1856. Min Range: -9.1856
Max Act: 8.6856. Min Act: -0.1700
Data Index: 6775459 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1856. Min Range: -9.1856
Max Act: 8.6231. Min Act: -0.1700
Data Index: 5576866 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1856. Min Range: -9.1856
Max Act: 8.6231. Min Act: -0.1700
Data Index: 3993101 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1856. Min Range: -9.1856
Max Act: 8.6231. Min Act: -0.1700
Data Index: 3642149 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1856. Min Range: -9.1856
Max Act: 8.5606. Min Act: -0.1700
Data Index: 5408104 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1856. Min Range: -9.1856
Max Act: 8.5606. Min Act: -0.1700
Data Index: 7061403 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1856. Min Range: -9.1856
Max Act: 8.5606. Min Act: -0.1699
Data Index: 7061414 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1856. Min Range: -9.1856
Max Act: 8.5606. Min Act: -0.1700
Data Index: 3610602 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1856. Min Range: -9.1856
Max Act: 8.5606. Min Act: -0.1700
Data Index: 3518330 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1856. Min Range: -9.1856
Max Act: 8.4981. Min Act: -0.1696
Data Index: 3993096 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1856. Min Range: -9.1856
Max Act: 8.4981. Min Act: -0.1700
Data Index: 682447 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #19