Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2224 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5683. Min Range: -8.5683
Max Act: 8.5683. Min Act: -0.1700
Data Index: 7601726 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5683. Min Range: -8.5683
Max Act: 8.5058. Min Act: -0.1700
Data Index: 6359506 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5683. Min Range: -8.5683
Max Act: 8.4433. Min Act: -0.1700
Data Index: 3506999 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5683. Min Range: -8.5683
Max Act: 8.3808. Min Act: -0.1700
Data Index: 6235559 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5683. Min Range: -8.5683
Max Act: 8.3808. Min Act: -0.1700
Data Index: 3527097 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5683. Min Range: -8.5683
Max Act: 8.2558. Min Act: -0.1700
Data Index: 5037882 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5683. Min Range: -8.5683
Max Act: 8.2558. Min Act: -0.1700
Data Index: 453315 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5683. Min Range: -8.5683
Max Act: 8.1933. Min Act: -0.1700
Data Index: 4014137 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5683. Min Range: -8.5683
Max Act: 8.1933. Min Act: -0.1700
Data Index: 6953013 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5683. Min Range: -8.5683
Max Act: 8.1308. Min Act: -0.1700
Data Index: 4081161 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5683. Min Range: -8.5683
Max Act: 8.1308. Min Act: -0.1700
Data Index: 2889053 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5683. Min Range: -8.5683
Max Act: 8.1308. Min Act: -0.1700
Data Index: 3127458 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5683. Min Range: -8.5683
Max Act: 8.0683. Min Act: -0.1700
Data Index: 3199729 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5683. Min Range: -8.5683
Max Act: 8.0058. Min Act: -0.1700
Data Index: 2515128 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5683. Min Range: -8.5683
Max Act: 8.0058. Min Act: -0.1700
Data Index: 1625109 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5683. Min Range: -8.5683
Max Act: 8.0058. Min Act: -0.1700
Data Index: 5422345 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5683. Min Range: -8.5683
Max Act: 8.0058. Min Act: -0.1700
Data Index: 3050485 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5683. Min Range: -8.5683
Max Act: 7.9433. Min Act: -0.1700
Data Index: 5799560 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5683. Min Range: -8.5683
Max Act: 7.8808. Min Act: -0.1700
Data Index: 6175505 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5683. Min Range: -8.5683
Max Act: 7.8808. Min Act: -0.1700
Data Index: 3648938 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19