Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3636 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9894. Min Range: -3.9894
Max Act: 3.9894. Min Act: -0.1700
Data Index: 5256302 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9894. Min Range: -3.9894
Max Act: 3.9582. Min Act: -0.1700
Data Index: 5399250 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9894. Min Range: -3.9894
Max Act: 3.9269. Min Act: -0.1700
Data Index: 5601768 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9894. Min Range: -3.9894
Max Act: 3.8956. Min Act: -0.1700
Data Index: 1799906 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9894. Min Range: -3.9894
Max Act: 3.8644. Min Act: -0.1700
Data Index: 8079865 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9894. Min Range: -3.9894
Max Act: 3.8018. Min Act: -0.1700
Data Index: 1799905 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9894. Min Range: -3.9894
Max Act: 3.8331. Min Act: -0.1700
Data Index: 5246984 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9894. Min Range: -3.9894
Max Act: 3.8331. Min Act: -0.1700
Data Index: 5975266 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9894. Min Range: -3.9894
Max Act: 3.8018. Min Act: -0.1700
Data Index: 4217415 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9894. Min Range: -3.9894
Max Act: 3.8018. Min Act: -0.1700
Data Index: 8528640 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9894. Min Range: -3.9894
Max Act: 3.7705. Min Act: -0.1700
Data Index: 2854413 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9894. Min Range: -3.9894
Max Act: 3.7705. Min Act: -0.1700
Data Index: 1756605 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9894. Min Range: -3.9894
Max Act: 3.7705. Min Act: -0.1700
Data Index: 6485169 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9894. Min Range: -3.9894
Max Act: 3.7393. Min Act: -0.1700
Data Index: 4413688 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9894. Min Range: -3.9894
Max Act: 3.7393. Min Act: -0.1700
Data Index: 1430060 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9894. Min Range: -3.9894
Max Act: 3.7393. Min Act: -0.1700
Data Index: 933400 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9894. Min Range: -3.9894
Max Act: 3.7393. Min Act: -0.1700
Data Index: 6281494 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9894. Min Range: -3.9894
Max Act: 3.7080. Min Act: -0.1700
Data Index: 5280467 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9894. Min Range: -3.9894
Max Act: 3.7080. Min Act: -0.1700
Data Index: 3893865 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9894. Min Range: -3.9894
Max Act: 3.7080. Min Act: -0.1700
Data Index: 3727235 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #19