Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3713 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3287. Min Range: -8.3287
Max Act: 8.3287. Min Act: -0.1700
Data Index: 4826494 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3287. Min Range: -8.3287
Max Act: 8.0162. Min Act: -0.1700
Data Index: 3093591 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3287. Min Range: -8.3287
Max Act: 7.9537. Min Act: -0.1700
Data Index: 3165992 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3287. Min Range: -8.3287
Max Act: 7.9537. Min Act: -0.1700
Data Index: 7653863 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3287. Min Range: -8.3287
Max Act: 7.8912. Min Act: -0.1700
Data Index: 2004255 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3287. Min Range: -8.3287
Max Act: 7.8912. Min Act: -0.1700
Data Index: 5217352 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3287. Min Range: -8.3287
Max Act: 7.8287. Min Act: -0.1700
Data Index: 4781945 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3287. Min Range: -8.3287
Max Act: 7.7662. Min Act: -0.1700
Data Index: 1619279 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3287. Min Range: -8.3287
Max Act: 7.7037. Min Act: -0.1700
Data Index: 1205294 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3287. Min Range: -8.3287
Max Act: 7.7037. Min Act: -0.1700
Data Index: 2481213 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3287. Min Range: -8.3287
Max Act: 7.7037. Min Act: -0.1700
Data Index: 4998500 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3287. Min Range: -8.3287
Max Act: 7.7037. Min Act: -0.1700
Data Index: 4033262 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3287. Min Range: -8.3287
Max Act: 7.7037. Min Act: -0.1700
Data Index: 2052380 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3287. Min Range: -8.3287
Max Act: 7.6412. Min Act: -0.1700
Data Index: 7429136 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3287. Min Range: -8.3287
Max Act: 7.6412. Min Act: -0.1700
Data Index: 2518576 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3287. Min Range: -8.3287
Max Act: 7.6412. Min Act: -0.1700
Data Index: 3904738 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3287. Min Range: -8.3287
Max Act: 7.5787. Min Act: -0.1700
Data Index: 3498138 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3287. Min Range: -8.3287
Max Act: 7.5787. Min Act: -0.1700
Data Index: 8315264 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3287. Min Range: -8.3287
Max Act: 7.5474. Min Act: -0.1700
Data Index: 1898827 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3287. Min Range: -8.3287
Max Act: 7.5474. Min Act: -0.1700
Data Index: 3271720 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #19