Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2125 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9769. Min Range: -7.9769
Max Act: 7.9769. Min Act: -0.1700
Data Index: 4292050 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9769. Min Range: -7.9769
Max Act: 7.8206. Min Act: -0.1700
Data Index: 5984993 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9769. Min Range: -7.9769
Max Act: 7.6644. Min Act: -0.1700
Data Index: 5347828 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9769. Min Range: -7.9769
Max Act: 7.6644. Min Act: -0.1700
Data Index: 4128745 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9769. Min Range: -7.9769
Max Act: 7.3206. Min Act: -0.1700
Data Index: 3973528 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9769. Min Range: -7.9769
Max Act: 7.2894. Min Act: -0.1700
Data Index: 2294805 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9769. Min Range: -7.9769
Max Act: 7.2581. Min Act: -0.1700
Data Index: 2372077 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9769. Min Range: -7.9769
Max Act: 7.2269. Min Act: -0.1700
Data Index: 327386 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9769. Min Range: -7.9769
Max Act: 7.1956. Min Act: -0.1700
Data Index: 6415010 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9769. Min Range: -7.9769
Max Act: 7.1331. Min Act: -0.1700
Data Index: 8578753 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9769. Min Range: -7.9769
Max Act: 7.1644. Min Act: -0.1700
Data Index: 5851651 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9769. Min Range: -7.9769
Max Act: 7.1019. Min Act: -0.1700
Data Index: 3729871 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9769. Min Range: -7.9769
Max Act: 7.0394. Min Act: -0.1700
Data Index: 55078 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9769. Min Range: -7.9769
Max Act: 7.0394. Min Act: -0.1700
Data Index: 7683035 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9769. Min Range: -7.9769
Max Act: 7.0081. Min Act: -0.1700
Data Index: 3765770 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9769. Min Range: -7.9769
Max Act: 6.9769. Min Act: -0.1700
Data Index: 5311291 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9769. Min Range: -7.9769
Max Act: 7.0081. Min Act: -0.1700
Data Index: 790855 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9769. Min Range: -7.9769
Max Act: 6.9769. Min Act: -0.1700
Data Index: 6547679 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9769. Min Range: -7.9769
Max Act: 6.9769. Min Act: -0.1700
Data Index: 1537473 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9769. Min Range: -7.9769
Max Act: 7.0081. Min Act: -0.1700
Data Index: 8022270 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19