Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2260 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0810. Min Range: -9.0810
Max Act: 9.0810. Min Act: -0.1700
Data Index: 7681920 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0810. Min Range: -9.0810
Max Act: 8.8310. Min Act: -0.1700
Data Index: 1175738 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0810. Min Range: -9.0810
Max Act: 8.5810. Min Act: -0.1700
Data Index: 499694 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0810. Min Range: -9.0810
Max Act: 8.5810. Min Act: -0.1700
Data Index: 1434441 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0810. Min Range: -9.0810
Max Act: 8.4560. Min Act: -0.1700
Data Index: 8091141 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0810. Min Range: -9.0810
Max Act: 8.5185. Min Act: -0.1700
Data Index: 7452640 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0810. Min Range: -9.0810
Max Act: 8.4560. Min Act: -0.1700
Data Index: 6841692 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0810. Min Range: -9.0810
Max Act: 8.4560. Min Act: -0.1700
Data Index: 4031183 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0810. Min Range: -9.0810
Max Act: 8.4560. Min Act: -0.1700
Data Index: 495353 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0810. Min Range: -9.0810
Max Act: 8.4560. Min Act: -0.1700
Data Index: 495354 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0810. Min Range: -9.0810
Max Act: 8.4560. Min Act: -0.1700
Data Index: 7112105 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0810. Min Range: -9.0810
Max Act: 8.4560. Min Act: -0.1700
Data Index: 7112106 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0810. Min Range: -9.0810
Max Act: 8.3935. Min Act: -0.1700
Data Index: 6178453 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0810. Min Range: -9.0810
Max Act: 8.4560. Min Act: -0.1700
Data Index: 5149729 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0810. Min Range: -9.0810
Max Act: 8.3935. Min Act: -0.1700
Data Index: 5316418 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0810. Min Range: -9.0810
Max Act: 8.3935. Min Act: -0.1700
Data Index: 3485317 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0810. Min Range: -9.0810
Max Act: 8.3935. Min Act: -0.1700
Data Index: 1912222 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0810. Min Range: -9.0810
Max Act: 8.3935. Min Act: -0.1700
Data Index: 4913320 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0810. Min Range: -9.0810
Max Act: 8.3310. Min Act: -0.1700
Data Index: 8091142 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0810. Min Range: -9.0810
Max Act: 8.3935. Min Act: -0.1700
Data Index: 384794 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #19