Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1287 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3873. Min Range: -5.3873
Max Act: 5.3873. Min Act: -0.1700
Data Index: 987931 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3873. Min Range: -5.3873
Max Act: 5.3248. Min Act: -0.1700
Data Index: 7744635 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3873. Min Range: -5.3873
Max Act: 5.2623. Min Act: -0.1700
Data Index: 4139511 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3873. Min Range: -5.3873
Max Act: 5.1686. Min Act: -0.1700
Data Index: 7247498 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3873. Min Range: -5.3873
Max Act: 5.1686. Min Act: -0.1700
Data Index: 3639097 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3873. Min Range: -5.3873
Max Act: 5.0436. Min Act: -0.1700
Data Index: 3341199 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3873. Min Range: -5.3873
Max Act: 5.0436. Min Act: -0.1700
Data Index: 3276893 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3873. Min Range: -5.3873
Max Act: 4.8873. Min Act: -0.1700
Data Index: 5620912 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3873. Min Range: -5.3873
Max Act: 4.9186. Min Act: -0.1700
Data Index: 8328177 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3873. Min Range: -5.3873
Max Act: 4.9186. Min Act: -0.1700
Data Index: 256132 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3873. Min Range: -5.3873
Max Act: 4.8873. Min Act: -0.1700
Data Index: 8828743 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3873. Min Range: -5.3873
Max Act: 4.8873. Min Act: -0.1700
Data Index: 3271467 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3873. Min Range: -5.3873
Max Act: 4.8561. Min Act: -0.1700
Data Index: 7912848 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3873. Min Range: -5.3873
Max Act: 4.8248. Min Act: -0.1700
Data Index: 1824234 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3873. Min Range: -5.3873
Max Act: 4.8561. Min Act: -0.1700
Data Index: 90326 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3873. Min Range: -5.3873
Max Act: 4.8248. Min Act: -0.1700
Data Index: 871083 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3873. Min Range: -5.3873
Max Act: 4.7936. Min Act: -0.1700
Data Index: 6354988 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3873. Min Range: -5.3873
Max Act: 4.8248. Min Act: -0.1700
Data Index: 6274343 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3873. Min Range: -5.3873
Max Act: 4.7623. Min Act: -0.1700
Data Index: 5305595 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3873. Min Range: -5.3873
Max Act: 4.7936. Min Act: -0.1700
Data Index: 8569 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19