Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2626 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.6453. Min Range: -9.6453
Max Act: 9.6453. Min Act: -0.1700
Data Index: 2599263 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6453. Min Range: -9.6453
Max Act: 9.2703. Min Act: -0.1700
Data Index: 3292676 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6453. Min Range: -9.6453
Max Act: 9.2078. Min Act: -0.1700
Data Index: 6165410 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6453. Min Range: -9.6453
Max Act: 9.0203. Min Act: -0.1700
Data Index: 4039006 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6453. Min Range: -9.6453
Max Act: 9.0828. Min Act: -0.1700
Data Index: 7215578 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6453. Min Range: -9.6453
Max Act: 8.9578. Min Act: -0.1700
Data Index: 2751383 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6453. Min Range: -9.6453
Max Act: 8.8328. Min Act: -0.1700
Data Index: 3325166 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6453. Min Range: -9.6453
Max Act: 8.8953. Min Act: -0.1700
Data Index: 4212312 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6453. Min Range: -9.6453
Max Act: 8.7703. Min Act: -0.1700
Data Index: 8537816 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6453. Min Range: -9.6453
Max Act: 8.7703. Min Act: -0.1700
Data Index: 5275828 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6453. Min Range: -9.6453
Max Act: 8.7703. Min Act: -0.1700
Data Index: 3606392 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6453. Min Range: -9.6453
Max Act: 8.7078. Min Act: -0.1700
Data Index: 3978641 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6453. Min Range: -9.6453
Max Act: 8.7078. Min Act: -0.1700
Data Index: 237502 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6453. Min Range: -9.6453
Max Act: 8.7078. Min Act: -0.1700
Data Index: 5757981 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6453. Min Range: -9.6453
Max Act: 8.7078. Min Act: -0.1700
Data Index: 6325024 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6453. Min Range: -9.6453
Max Act: 8.6453. Min Act: -0.1700
Data Index: 2397575 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6453. Min Range: -9.6453
Max Act: 8.6453. Min Act: -0.1700
Data Index: 5226107 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6453. Min Range: -9.6453
Max Act: 8.6453. Min Act: -0.1700
Data Index: 5525739 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6453. Min Range: -9.6453
Max Act: 8.6453. Min Act: -0.1700
Data Index: 8456136 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6453. Min Range: -9.6453
Max Act: 8.6453. Min Act: -0.1700
Data Index: 6150595 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19