Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2012 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9493. Min Range: -6.9493
Max Act: 6.9493. Min Act: -0.1700
Data Index: 8063564 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9493. Min Range: -6.9493
Max Act: 6.9493. Min Act: -0.1700
Data Index: 850106 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9493. Min Range: -6.9493
Max Act: 6.8868. Min Act: -0.1700
Data Index: 7298453 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9493. Min Range: -6.9493
Max Act: 6.8556. Min Act: -0.1700
Data Index: 512559 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9493. Min Range: -6.9493
Max Act: 6.6368. Min Act: -0.1700
Data Index: 6620870 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9493. Min Range: -6.9493
Max Act: 6.6056. Min Act: -0.1700
Data Index: 7953128 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9493. Min Range: -6.9493
Max Act: 6.6368. Min Act: -0.1700
Data Index: 2990628 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9493. Min Range: -6.9493
Max Act: 6.5743. Min Act: -0.1700
Data Index: 5745006 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9493. Min Range: -6.9493
Max Act: 6.6368. Min Act: -0.1700
Data Index: 1485883 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9493. Min Range: -6.9493
Max Act: 6.5743. Min Act: -0.1700
Data Index: 2221844 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9493. Min Range: -6.9493
Max Act: 6.5431. Min Act: -0.1700
Data Index: 5270596 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9493. Min Range: -6.9493
Max Act: 6.5431. Min Act: -0.1700
Data Index: 2345468 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9493. Min Range: -6.9493
Max Act: 6.5743. Min Act: -0.1700
Data Index: 7060870 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9493. Min Range: -6.9493
Max Act: 6.5743. Min Act: -0.1700
Data Index: 1073633 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9493. Min Range: -6.9493
Max Act: 6.5743. Min Act: -0.1700
Data Index: 3954616 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9493. Min Range: -6.9493
Max Act: 6.4806. Min Act: -0.1700
Data Index: 6358909 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9493. Min Range: -6.9493
Max Act: 6.4806. Min Act: -0.1700
Data Index: 6004148 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9493. Min Range: -6.9493
Max Act: 6.4806. Min Act: -0.1700
Data Index: 3235426 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9493. Min Range: -6.9493
Max Act: 6.4806. Min Act: -0.1700
Data Index: 5815028 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9493. Min Range: -6.9493
Max Act: 6.3868. Min Act: -0.1700
Data Index: 5279478 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #19