Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3579 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0653. Min Range: -6.0653
Max Act: 6.0653. Min Act: -0.1700
Data Index: 5739168 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0653. Min Range: -6.0653
Max Act: 6.0341. Min Act: -0.1700
Data Index: 1575439 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0653. Min Range: -6.0653
Max Act: 6.0341. Min Act: -0.1700
Data Index: 8011547 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0653. Min Range: -6.0653
Max Act: 5.9403. Min Act: -0.1700
Data Index: 956543 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0653. Min Range: -6.0653
Max Act: 5.9403. Min Act: -0.1700
Data Index: 678119 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0653. Min Range: -6.0653
Max Act: 5.9091. Min Act: -0.1700
Data Index: 8812114 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0653. Min Range: -6.0653
Max Act: 5.9091. Min Act: -0.1700
Data Index: 8715150 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0653. Min Range: -6.0653
Max Act: 5.9091. Min Act: -0.1700
Data Index: 8433179 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0653. Min Range: -6.0653
Max Act: 5.8778. Min Act: -0.1700
Data Index: 6204812 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0653. Min Range: -6.0653
Max Act: 5.8466. Min Act: -0.1700
Data Index: 8540332 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0653. Min Range: -6.0653
Max Act: 5.8466. Min Act: -0.1700
Data Index: 8828200 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0653. Min Range: -6.0653
Max Act: 5.8466. Min Act: -0.1700
Data Index: 8643546 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0653. Min Range: -6.0653
Max Act: 5.8778. Min Act: -0.1700
Data Index: 2147358 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0653. Min Range: -6.0653
Max Act: 5.8778. Min Act: -0.1700
Data Index: 4768489 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0653. Min Range: -6.0653
Max Act: 5.8778. Min Act: -0.1700
Data Index: 3684715 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0653. Min Range: -6.0653
Max Act: 5.8778. Min Act: -0.1700
Data Index: 6305747 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0653. Min Range: -6.0653
Max Act: 5.8466. Min Act: -0.1700
Data Index: 1501218 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0653. Min Range: -6.0653
Max Act: 5.8153. Min Act: -0.1700
Data Index: 2255622 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0653. Min Range: -6.0653
Max Act: 5.8153. Min Act: -0.1700
Data Index: 3387108 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0653. Min Range: -6.0653
Max Act: 5.8778. Min Act: -0.1700
Data Index: 3252866 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #19