Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5245 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7412. Min Range: -6.7412
Max Act: 6.7412. Min Act: -0.1700
Data Index: 6336739 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7412. Min Range: -6.7412
Max Act: 6.6787. Min Act: -0.1700
Data Index: 3810927 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7412. Min Range: -6.7412
Max Act: 6.6474. Min Act: -0.1700
Data Index: 2907869 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7412. Min Range: -6.7412
Max Act: 6.5224. Min Act: -0.1700
Data Index: 2441095 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7412. Min Range: -6.7412
Max Act: 6.4912. Min Act: -0.1700
Data Index: 1757164 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7412. Min Range: -6.7412
Max Act: 6.4599. Min Act: -0.1700
Data Index: 3205452 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7412. Min Range: -6.7412
Max Act: 6.3974. Min Act: -0.1700
Data Index: 3463823 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7412. Min Range: -6.7412
Max Act: 6.3662. Min Act: -0.1700
Data Index: 1273095 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7412. Min Range: -6.7412
Max Act: 6.3974. Min Act: -0.1700
Data Index: 6390326 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7412. Min Range: -6.7412
Max Act: 6.3974. Min Act: -0.1700
Data Index: 4399788 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7412. Min Range: -6.7412
Max Act: 6.3662. Min Act: -0.1700
Data Index: 4722479 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7412. Min Range: -6.7412
Max Act: 6.3037. Min Act: -0.1700
Data Index: 4198382 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7412. Min Range: -6.7412
Max Act: 6.2724. Min Act: -0.1700
Data Index: 1791833 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7412. Min Range: -6.7412
Max Act: 6.2412. Min Act: -0.1700
Data Index: 8373700 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7412. Min Range: -6.7412
Max Act: 6.2099. Min Act: -0.1700
Data Index: 3470489 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7412. Min Range: -6.7412
Max Act: 6.2099. Min Act: -0.1700
Data Index: 1098077 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7412. Min Range: -6.7412
Max Act: 6.2412. Min Act: -0.1700
Data Index: 493971 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7412. Min Range: -6.7412
Max Act: 6.2099. Min Act: -0.1700
Data Index: 4795020 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7412. Min Range: -6.7412
Max Act: 6.1474. Min Act: -0.1700
Data Index: 2760534 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7412. Min Range: -6.7412
Max Act: 6.1162. Min Act: -0.1700
Data Index: 3326734 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19