Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3038 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0606. Min Range: -10.0606
Max Act: 10.0606. Min Act: -0.1700
Data Index: 4870697 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0606. Min Range: -10.0606
Max Act: 9.9356. Min Act: -0.1700
Data Index: 7615517 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0606. Min Range: -10.0606
Max Act: 9.9356. Min Act: -0.1700
Data Index: 5395442 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0606. Min Range: -10.0606
Max Act: 9.8731. Min Act: -0.1700
Data Index: 2913620 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0606. Min Range: -10.0606
Max Act: 9.8106. Min Act: -0.1700
Data Index: 7286191 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0606. Min Range: -10.0606
Max Act: 9.8106. Min Act: -0.1700
Data Index: 1829718 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0606. Min Range: -10.0606
Max Act: 9.7481. Min Act: -0.1700
Data Index: 6407498 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0606. Min Range: -10.0606
Max Act: 9.7481. Min Act: -0.1700
Data Index: 1668327 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0606. Min Range: -10.0606
Max Act: 9.6856. Min Act: -0.1700
Data Index: 6013472 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0606. Min Range: -10.0606
Max Act: 9.6856. Min Act: -0.1700
Data Index: 3412793 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0606. Min Range: -10.0606
Max Act: 9.6856. Min Act: -0.1700
Data Index: 8149381 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0606. Min Range: -10.0606
Max Act: 9.6231. Min Act: -0.1700
Data Index: 8191723 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0606. Min Range: -10.0606
Max Act: 9.6856. Min Act: -0.1700
Data Index: 5279509 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0606. Min Range: -10.0606
Max Act: 9.6231. Min Act: -0.1700
Data Index: 5758950 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0606. Min Range: -10.0606
Max Act: 9.6231. Min Act: -0.1700
Data Index: 2812113 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0606. Min Range: -10.0606
Max Act: 9.6231. Min Act: -0.1700
Data Index: 1492589 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0606. Min Range: -10.0606
Max Act: 9.6231. Min Act: -0.1700
Data Index: 8280850 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0606. Min Range: -10.0606
Max Act: 9.6231. Min Act: -0.1700
Data Index: 3477739 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0606. Min Range: -10.0606
Max Act: 9.6231. Min Act: -0.1700
Data Index: 585799 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0606. Min Range: -10.0606
Max Act: 9.5606. Min Act: -0.1700
Data Index: 1222890 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #19