Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 155 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1102. Min Range: -5.1102
Max Act: 5.1102. Min Act: -0.1700
Data Index: 7693433 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1102. Min Range: -5.1102
Max Act: 5.1102. Min Act: -0.1700
Data Index: 8394085 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1102. Min Range: -5.1102
Max Act: 5.0477. Min Act: -0.1700
Data Index: 6162256 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1102. Min Range: -5.1102
Max Act: 5.0165. Min Act: -0.1700
Data Index: 803397 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1102. Min Range: -5.1102
Max Act: 4.9852. Min Act: -0.1700
Data Index: 840741 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1102. Min Range: -5.1102
Max Act: 4.9540. Min Act: -0.1700
Data Index: 4561604 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1102. Min Range: -5.1102
Max Act: 4.9540. Min Act: -0.1700
Data Index: 3538676 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1102. Min Range: -5.1102
Max Act: 4.9540. Min Act: -0.1700
Data Index: 2860670 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1102. Min Range: -5.1102
Max Act: 4.9227. Min Act: -0.1700
Data Index: 4995279 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1102. Min Range: -5.1102
Max Act: 4.9227. Min Act: -0.1700
Data Index: 4216714 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1102. Min Range: -5.1102
Max Act: 4.9227. Min Act: -0.1700
Data Index: 4991953 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1102. Min Range: -5.1102
Max Act: 4.8915. Min Act: -0.1700
Data Index: 3031424 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1102. Min Range: -5.1102
Max Act: 4.8915. Min Act: -0.1700
Data Index: 3066677 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1102. Min Range: -5.1102
Max Act: 4.8915. Min Act: -0.1700
Data Index: 3082533 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1102. Min Range: -5.1102
Max Act: 4.8290. Min Act: -0.1700
Data Index: 2731091 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1102. Min Range: -5.1102
Max Act: 4.8602. Min Act: -0.1700
Data Index: 3239865 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1102. Min Range: -5.1102
Max Act: 4.7977. Min Act: -0.1700
Data Index: 8085236 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1102. Min Range: -5.1102
Max Act: 4.8602. Min Act: -0.1700
Data Index: 416107 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1102. Min Range: -5.1102
Max Act: 4.7977. Min Act: -0.1700
Data Index: 7306604 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1102. Min Range: -5.1102
Max Act: 4.7977. Min Act: -0.1700
Data Index: 3307612 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19