Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3811 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6891. Min Range: -7.6891
Max Act: 7.6891. Min Act: -0.1700
Data Index: 4014586 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6891. Min Range: -7.6891
Max Act: 7.4704. Min Act: -0.1700
Data Index: 5728234 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6891. Min Range: -7.6891
Max Act: 7.3766. Min Act: -0.1700
Data Index: 4575555 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6891. Min Range: -7.6891
Max Act: 7.2516. Min Act: -0.1700
Data Index: 6147571 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6891. Min Range: -7.6891
Max Act: 7.2516. Min Act: -0.1700
Data Index: 7513383 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6891. Min Range: -7.6891
Max Act: 7.2516. Min Act: -0.1700
Data Index: 1772288 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6891. Min Range: -7.6891
Max Act: 7.2516. Min Act: -0.1700
Data Index: 4332371 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6891. Min Range: -7.6891
Max Act: 7.2516. Min Act: -0.1700
Data Index: 7609813 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6891. Min Range: -7.6891
Max Act: 7.2204. Min Act: -0.1700
Data Index: 8196495 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6891. Min Range: -7.6891
Max Act: 7.2204. Min Act: -0.1700
Data Index: 4090921 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6891. Min Range: -7.6891
Max Act: 7.1579. Min Act: -0.1700
Data Index: 7030733 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6891. Min Range: -7.6891
Max Act: 7.0954. Min Act: -0.1700
Data Index: 5246914 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6891. Min Range: -7.6891
Max Act: 7.1266. Min Act: -0.1700
Data Index: 7170344 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6891. Min Range: -7.6891
Max Act: 7.0954. Min Act: -0.1700
Data Index: 3692220 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6891. Min Range: -7.6891
Max Act: 7.0641. Min Act: -0.1700
Data Index: 7480771 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6891. Min Range: -7.6891
Max Act: 7.0329. Min Act: -0.1700
Data Index: 8455059 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6891. Min Range: -7.6891
Max Act: 7.0329. Min Act: -0.1700
Data Index: 3579547 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6891. Min Range: -7.6891
Max Act: 7.0329. Min Act: -0.1700
Data Index: 8689210 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6891. Min Range: -7.6891
Max Act: 7.0329. Min Act: -0.1700
Data Index: 6453940 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6891. Min Range: -7.6891
Max Act: 7.0016. Min Act: -0.1700
Data Index: 3044478 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #19