Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4076 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.4616. Min Range: -1.4616
Max Act: 1.4616. Min Act: -0.1700
Data Index: 5423313 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4616. Min Range: -1.4616
Max Act: 1.4264. Min Act: -0.1700
Data Index: 5395995 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4616. Min Range: -1.4616
Max Act: 1.3912. Min Act: -0.1700
Data Index: 8222971 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4616. Min Range: -1.4616
Max Act: 1.3912. Min Act: -0.1700
Data Index: 6486773 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4616. Min Range: -1.4616
Max Act: 1.3912. Min Act: -0.1700
Data Index: 3794246 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4616. Min Range: -1.4616
Max Act: 1.3912. Min Act: -0.1700
Data Index: 466828 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4616. Min Range: -1.4616
Max Act: 1.3560. Min Act: -0.1700
Data Index: 5696033 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4616. Min Range: -1.4616
Max Act: 1.3912. Min Act: -0.1700
Data Index: 2602470 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4616. Min Range: -1.4616
Max Act: 1.3736. Min Act: -0.1700
Data Index: 4236598 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4616. Min Range: -1.4616
Max Act: 1.3560. Min Act: -0.1700
Data Index: 8530781 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4616. Min Range: -1.4616
Max Act: 1.3560. Min Act: -0.1700
Data Index: 8518347 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4616. Min Range: -1.4616
Max Act: 1.3383. Min Act: -0.1700
Data Index: 4267934 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4616. Min Range: -1.4616
Max Act: 1.3383. Min Act: -0.1700
Data Index: 4881747 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4616. Min Range: -1.4616
Max Act: 1.3383. Min Act: -0.1700
Data Index: 4057020 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4616. Min Range: -1.4616
Max Act: 1.3383. Min Act: -0.1700
Data Index: 1895233 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4616. Min Range: -1.4616
Max Act: 1.3560. Min Act: -0.1700
Data Index: 5470471 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4616. Min Range: -1.4616
Max Act: 1.3560. Min Act: -0.1700
Data Index: 5501221 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4616. Min Range: -1.4616
Max Act: 1.3560. Min Act: -0.1700
Data Index: 654515 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4616. Min Range: -1.4616
Max Act: 1.3383. Min Act: -0.1700
Data Index: 5527752 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4616. Min Range: -1.4616
Max Act: 1.3383. Min Act: -0.1700
Data Index: 796971 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19