Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3207 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3497. Min Range: -5.3497
Max Act: 5.3497. Min Act: -0.1700
Data Index: 2846549 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3497. Min Range: -5.3497
Max Act: 5.1309. Min Act: -0.1700
Data Index: 8071666 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3497. Min Range: -5.3497
Max Act: 5.0372. Min Act: -0.1700
Data Index: 593028 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3497. Min Range: -5.3497
Max Act: 5.0372. Min Act: -0.1700
Data Index: 4890777 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3497. Min Range: -5.3497
Max Act: 5.0059. Min Act: -0.1700
Data Index: 4094835 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3497. Min Range: -5.3497
Max Act: 5.0059. Min Act: -0.1700
Data Index: 1692631 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3497. Min Range: -5.3497
Max Act: 4.9747. Min Act: -0.1700
Data Index: 3239121 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3497. Min Range: -5.3497
Max Act: 4.9434. Min Act: -0.1700
Data Index: 3765709 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3497. Min Range: -5.3497
Max Act: 4.9434. Min Act: -0.1700
Data Index: 3673865 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3497. Min Range: -5.3497
Max Act: 4.9434. Min Act: -0.1700
Data Index: 7712214 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3497. Min Range: -5.3497
Max Act: 4.9434. Min Act: -0.1700
Data Index: 8815142 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3497. Min Range: -5.3497
Max Act: 4.9122. Min Act: -0.1700
Data Index: 8112188 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3497. Min Range: -5.3497
Max Act: 4.9122. Min Act: -0.1700
Data Index: 2768034 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3497. Min Range: -5.3497
Max Act: 4.9122. Min Act: -0.1700
Data Index: 467175 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3497. Min Range: -5.3497
Max Act: 4.9122. Min Act: -0.1700
Data Index: 8577117 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3497. Min Range: -5.3497
Max Act: 4.9122. Min Act: -0.1700
Data Index: 7784969 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3497. Min Range: -5.3497
Max Act: 4.9122. Min Act: -0.1700
Data Index: 2274954 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3497. Min Range: -5.3497
Max Act: 4.8809. Min Act: -0.1700
Data Index: 7673950 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3497. Min Range: -5.3497
Max Act: 4.8809. Min Act: -0.1700
Data Index: 6306595 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3497. Min Range: -5.3497
Max Act: 4.8809. Min Act: -0.1700
Data Index: 1068587 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19