Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 880 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7707. Min Range: -7.7707
Max Act: 7.7707. Min Act: -0.1700
Data Index: 108985 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7707. Min Range: -7.7707
Max Act: 7.2394. Min Act: -0.1700
Data Index: 3460102 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7707. Min Range: -7.7707
Max Act: 7.1144. Min Act: -0.1700
Data Index: 459943 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7707. Min Range: -7.7707
Max Act: 7.1144. Min Act: -0.1700
Data Index: 2860254 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7707. Min Range: -7.7707
Max Act: 7.0519. Min Act: -0.1700
Data Index: 8197981 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7707. Min Range: -7.7707
Max Act: 7.0207. Min Act: -0.1700
Data Index: 4754125 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7707. Min Range: -7.7707
Max Act: 6.9894. Min Act: -0.1700
Data Index: 4454515 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7707. Min Range: -7.7707
Max Act: 6.9894. Min Act: -0.1700
Data Index: 8695783 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7707. Min Range: -7.7707
Max Act: 6.9894. Min Act: -0.1700
Data Index: 164808 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7707. Min Range: -7.7707
Max Act: 6.9894. Min Act: -0.1700
Data Index: 5474640 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7707. Min Range: -7.7707
Max Act: 6.9582. Min Act: -0.1700
Data Index: 4599942 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7707. Min Range: -7.7707
Max Act: 6.9582. Min Act: -0.1700
Data Index: 2789118 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7707. Min Range: -7.7707
Max Act: 6.9269. Min Act: -0.1700
Data Index: 5681462 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7707. Min Range: -7.7707
Max Act: 6.8957. Min Act: -0.1700
Data Index: 6551095 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7707. Min Range: -7.7707
Max Act: 6.9269. Min Act: -0.1700
Data Index: 808605 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7707. Min Range: -7.7707
Max Act: 6.9269. Min Act: -0.1700
Data Index: 1733955 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7707. Min Range: -7.7707
Max Act: 6.8957. Min Act: -0.1700
Data Index: 3351450 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7707. Min Range: -7.7707
Max Act: 6.8957. Min Act: -0.1700
Data Index: 8118411 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7707. Min Range: -7.7707
Max Act: 6.8644. Min Act: -0.1700
Data Index: 4167706 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7707. Min Range: -7.7707
Max Act: 6.8644. Min Act: -0.1700
Data Index: 6418144 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #19