Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3910 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4700. Min Range: -4.4700
Max Act: 4.4700. Min Act: -0.1700
Data Index: 6458819 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4700. Min Range: -4.4700
Max Act: 4.3137. Min Act: -0.1700
Data Index: 8704402 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4700. Min Range: -4.4700
Max Act: 4.3137. Min Act: -0.1700
Data Index: 4117338 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4700. Min Range: -4.4700
Max Act: 4.2512. Min Act: -0.1700
Data Index: 7509159 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4700. Min Range: -4.4700
Max Act: 4.2200. Min Act: -0.1700
Data Index: 1476019 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4700. Min Range: -4.4700
Max Act: 4.1575. Min Act: -0.1700
Data Index: 376112 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4700. Min Range: -4.4700
Max Act: 4.1262. Min Act: -0.1700
Data Index: 2235036 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4700. Min Range: -4.4700
Max Act: 4.1575. Min Act: -0.1700
Data Index: 741813 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4700. Min Range: -4.4700
Max Act: 4.1575. Min Act: -0.1700
Data Index: 6492755 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4700. Min Range: -4.4700
Max Act: 4.1262. Min Act: -0.1700
Data Index: 1784272 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4700. Min Range: -4.4700
Max Act: 4.1262. Min Act: -0.1700
Data Index: 4427764 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4700. Min Range: -4.4700
Max Act: 4.1575. Min Act: -0.1700
Data Index: 2901785 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4700. Min Range: -4.4700
Max Act: 4.1575. Min Act: -0.1700
Data Index: 5191643 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4700. Min Range: -4.4700
Max Act: 4.0950. Min Act: -0.1700
Data Index: 2045622 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4700. Min Range: -4.4700
Max Act: 4.1575. Min Act: -0.1700
Data Index: 6096279 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4700. Min Range: -4.4700
Max Act: 4.0950. Min Act: -0.1700
Data Index: 8505808 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4700. Min Range: -4.4700
Max Act: 4.1262. Min Act: -0.1700
Data Index: 3439662 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4700. Min Range: -4.4700
Max Act: 4.0637. Min Act: -0.1700
Data Index: 5197675 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4700. Min Range: -4.4700
Max Act: 4.1262. Min Act: -0.1700
Data Index: 7576356 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4700. Min Range: -4.4700
Max Act: 4.0950. Min Act: -0.1700
Data Index: 7576832 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #19