Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 792 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1862. Min Range: -7.1862
Max Act: 7.1862. Min Act: -0.1700
Data Index: 8605661 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1862. Min Range: -7.1862
Max Act: 7.0925. Min Act: -0.1700
Data Index: 339258 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1862. Min Range: -7.1862
Max Act: 7.0925. Min Act: -0.1700
Data Index: 3035678 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1862. Min Range: -7.1862
Max Act: 7.0925. Min Act: -0.1700
Data Index: 4815245 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1862. Min Range: -7.1862
Max Act: 7.0300. Min Act: -0.1700
Data Index: 3679485 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1862. Min Range: -7.1862
Max Act: 7.0300. Min Act: -0.1700
Data Index: 4744785 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1862. Min Range: -7.1862
Max Act: 6.9987. Min Act: -0.1700
Data Index: 8152508 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1862. Min Range: -7.1862
Max Act: 6.9050. Min Act: -0.1700
Data Index: 5517553 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1862. Min Range: -7.1862
Max Act: 6.9050. Min Act: -0.1700
Data Index: 7095506 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1862. Min Range: -7.1862
Max Act: 6.9362. Min Act: -0.1700
Data Index: 6024914 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1862. Min Range: -7.1862
Max Act: 6.8737. Min Act: -0.1700
Data Index: 4634624 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1862. Min Range: -7.1862
Max Act: 6.8737. Min Act: -0.1700
Data Index: 2051270 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1862. Min Range: -7.1862
Max Act: 6.8112. Min Act: -0.1700
Data Index: 6475431 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1862. Min Range: -7.1862
Max Act: 6.7800. Min Act: -0.1700
Data Index: 2414427 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1862. Min Range: -7.1862
Max Act: 6.7487. Min Act: -0.1700
Data Index: 4988453 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1862. Min Range: -7.1862
Max Act: 6.7175. Min Act: -0.1700
Data Index: 6296957 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1862. Min Range: -7.1862
Max Act: 6.7800. Min Act: -0.1700
Data Index: 1678390 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1862. Min Range: -7.1862
Max Act: 6.7487. Min Act: -0.1700
Data Index: 270940 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1862. Min Range: -7.1862
Max Act: 6.7175. Min Act: -0.1700
Data Index: 6089315 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1862. Min Range: -7.1862
Max Act: 6.7175. Min Act: -0.1700
Data Index: 65485 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19