Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3159 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2276. Min Range: -9.2276
Max Act: 9.2276. Min Act: -0.1700
Data Index: 3445396 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2276. Min Range: -9.2276
Max Act: 8.7901. Min Act: -0.1700
Data Index: 7405706 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2276. Min Range: -9.2276
Max Act: 8.7276. Min Act: -0.1700
Data Index: 1622443 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2276. Min Range: -9.2276
Max Act: 8.6651. Min Act: -0.1700
Data Index: 5220665 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2276. Min Range: -9.2276
Max Act: 8.5401. Min Act: -0.1700
Data Index: 509541 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2276. Min Range: -9.2276
Max Act: 8.5401. Min Act: -0.1700
Data Index: 7296218 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2276. Min Range: -9.2276
Max Act: 8.5401. Min Act: -0.1700
Data Index: 8790754 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2276. Min Range: -9.2276
Max Act: 8.2901. Min Act: -0.1700
Data Index: 6459120 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2276. Min Range: -9.2276
Max Act: 8.1651. Min Act: -0.1700
Data Index: 1396208 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2276. Min Range: -9.2276
Max Act: 8.1026. Min Act: -0.1700
Data Index: 2828691 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2276. Min Range: -9.2276
Max Act: 7.9776. Min Act: -0.1700
Data Index: 1058555 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2276. Min Range: -9.2276
Max Act: 7.9151. Min Act: -0.1700
Data Index: 6666114 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2276. Min Range: -9.2276
Max Act: 7.9151. Min Act: -0.1700
Data Index: 6375672 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2276. Min Range: -9.2276
Max Act: 7.9151. Min Act: -0.1700
Data Index: 202085 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2276. Min Range: -9.2276
Max Act: 7.9151. Min Act: -0.1700
Data Index: 2446775 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2276. Min Range: -9.2276
Max Act: 7.9151. Min Act: -0.1700
Data Index: 5708854 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2276. Min Range: -9.2276
Max Act: 7.9151. Min Act: -0.1700
Data Index: 5671669 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2276. Min Range: -9.2276
Max Act: 7.8526. Min Act: -0.1700
Data Index: 6226 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2276. Min Range: -9.2276
Max Act: 7.9151. Min Act: -0.1700
Data Index: 830038 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2276. Min Range: -9.2276
Max Act: 7.9151. Min Act: -0.1700
Data Index: 8578173 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #19