Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4502 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6401. Min Range: -7.6401
Max Act: 7.6401. Min Act: -0.1700
Data Index: 5794268 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6401. Min Range: -7.6401
Max Act: 7.4526. Min Act: -0.1700
Data Index: 2163743 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6401. Min Range: -7.6401
Max Act: 7.2339. Min Act: -0.1700
Data Index: 5483544 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6401. Min Range: -7.6401
Max Act: 7.1089. Min Act: -0.1700
Data Index: 5153898 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6401. Min Range: -7.6401
Max Act: 7.0151. Min Act: -0.1700
Data Index: 6484644 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6401. Min Range: -7.6401
Max Act: 6.9839. Min Act: -0.1700
Data Index: 6221916 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6401. Min Range: -7.6401
Max Act: 6.9839. Min Act: -0.1700
Data Index: 3020805 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6401. Min Range: -7.6401
Max Act: 6.9839. Min Act: -0.1700
Data Index: 8802210 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6401. Min Range: -7.6401
Max Act: 6.9214. Min Act: -0.1700
Data Index: 8678875 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6401. Min Range: -7.6401
Max Act: 6.9214. Min Act: -0.1700
Data Index: 7305992 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6401. Min Range: -7.6401
Max Act: 6.8589. Min Act: -0.1700
Data Index: 767057 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6401. Min Range: -7.6401
Max Act: 6.8276. Min Act: -0.1700
Data Index: 7832225 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6401. Min Range: -7.6401
Max Act: 6.7964. Min Act: -0.1700
Data Index: 603828 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6401. Min Range: -7.6401
Max Act: 6.7964. Min Act: -0.1700
Data Index: 5138244 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6401. Min Range: -7.6401
Max Act: 6.7964. Min Act: -0.1700
Data Index: 5289732 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6401. Min Range: -7.6401
Max Act: 6.7964. Min Act: -0.1700
Data Index: 1494162 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6401. Min Range: -7.6401
Max Act: 6.7339. Min Act: -0.1700
Data Index: 2368761 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6401. Min Range: -7.6401
Max Act: 6.7651. Min Act: -0.1700
Data Index: 7556341 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6401. Min Range: -7.6401
Max Act: 6.7339. Min Act: -0.1700
Data Index: 1698814 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6401. Min Range: -7.6401
Max Act: 6.7339. Min Act: -0.1700
Data Index: 4281554 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #19