Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2613 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.1423. Min Range: -8.1423
Max Act: 8.1423. Min Act: -0.1700
Data Index: 5923749 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1423. Min Range: -8.1423
Max Act: 8.0798. Min Act: -0.1700
Data Index: 6875661 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1423. Min Range: -8.1423
Max Act: 8.0173. Min Act: -0.1700
Data Index: 5354860 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1423. Min Range: -8.1423
Max Act: 7.9548. Min Act: -0.1700
Data Index: 5687119 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1423. Min Range: -8.1423
Max Act: 7.8923. Min Act: -0.1700
Data Index: 8163706 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1423. Min Range: -8.1423
Max Act: 7.8298. Min Act: -0.1700
Data Index: 5135644 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1423. Min Range: -8.1423
Max Act: 7.8298. Min Act: -0.1700
Data Index: 3368299 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1423. Min Range: -8.1423
Max Act: 7.7673. Min Act: -0.1700
Data Index: 5149128 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1423. Min Range: -8.1423
Max Act: 7.7673. Min Act: -0.1700
Data Index: 4619063 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1423. Min Range: -8.1423
Max Act: 7.7673. Min Act: -0.1700
Data Index: 1741173 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1423. Min Range: -8.1423
Max Act: 7.7673. Min Act: -0.1700
Data Index: 4257051 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1423. Min Range: -8.1423
Max Act: 7.7673. Min Act: -0.1700
Data Index: 4251497 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1423. Min Range: -8.1423
Max Act: 7.7048. Min Act: -0.1700
Data Index: 381948 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1423. Min Range: -8.1423
Max Act: 7.7048. Min Act: -0.1700
Data Index: 4048742 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1423. Min Range: -8.1423
Max Act: 7.6423. Min Act: -0.1700
Data Index: 4167257 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1423. Min Range: -8.1423
Max Act: 7.6423. Min Act: -0.1700
Data Index: 5823581 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1423. Min Range: -8.1423
Max Act: 7.6423. Min Act: -0.1700
Data Index: 839474 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1423. Min Range: -8.1423
Max Act: 7.6423. Min Act: -0.1700
Data Index: 4052597 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1423. Min Range: -8.1423
Max Act: 7.6423. Min Act: -0.1700
Data Index: 1709571 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1423. Min Range: -8.1423
Max Act: 7.6423. Min Act: -0.1700
Data Index: 5687963 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19