Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2233 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9874. Min Range: -6.9874
Max Act: 6.9874. Min Act: -0.1700
Data Index: 7647428 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9874. Min Range: -6.9874
Max Act: 6.8936. Min Act: -0.1700
Data Index: 8247325 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9874. Min Range: -6.9874
Max Act: 6.8624. Min Act: -0.1700
Data Index: 5276489 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9874. Min Range: -6.9874
Max Act: 6.7999. Min Act: -0.1700
Data Index: 6662642 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9874. Min Range: -6.9874
Max Act: 6.7999. Min Act: -0.1700
Data Index: 647776 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9874. Min Range: -6.9874
Max Act: 6.7686. Min Act: -0.1700
Data Index: 3623368 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9874. Min Range: -6.9874
Max Act: 6.7686. Min Act: -0.1700
Data Index: 617656 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9874. Min Range: -6.9874
Max Act: 6.7686. Min Act: -0.1700
Data Index: 438671 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9874. Min Range: -6.9874
Max Act: 6.7374. Min Act: -0.1700
Data Index: 4567454 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9874. Min Range: -6.9874
Max Act: 6.7061. Min Act: -0.1700
Data Index: 1279604 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9874. Min Range: -6.9874
Max Act: 6.6749. Min Act: -0.1700
Data Index: 6764261 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9874. Min Range: -6.9874
Max Act: 6.6436. Min Act: -0.1700
Data Index: 8805582 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9874. Min Range: -6.9874
Max Act: 6.6436. Min Act: -0.1700
Data Index: 3187182 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9874. Min Range: -6.9874
Max Act: 6.6124. Min Act: -0.1700
Data Index: 8674002 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9874. Min Range: -6.9874
Max Act: 6.5811. Min Act: -0.1700
Data Index: 3934706 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9874. Min Range: -6.9874
Max Act: 6.5499. Min Act: -0.1700
Data Index: 109690 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9874. Min Range: -6.9874
Max Act: 6.5811. Min Act: -0.1700
Data Index: 1004516 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9874. Min Range: -6.9874
Max Act: 6.5811. Min Act: -0.1700
Data Index: 8096087 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9874. Min Range: -6.9874
Max Act: 6.5499. Min Act: -0.1700
Data Index: 6519341 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9874. Min Range: -6.9874
Max Act: 6.5811. Min Act: -0.1700
Data Index: 1697710 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #19