Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2622 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5027. Min Range: -3.5027
Max Act: 3.5027. Min Act: -0.1700
Data Index: 1551448 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5027. Min Range: -3.5027
Max Act: 3.3616. Min Act: -0.1700
Data Index: 1538281 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5027. Min Range: -3.5027
Max Act: 3.3459. Min Act: -0.1700
Data Index: 462875 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5027. Min Range: -3.5027
Max Act: 3.2989. Min Act: -0.1700
Data Index: 6466871 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5027. Min Range: -3.5027
Max Act: 3.2675. Min Act: -0.1700
Data Index: 3214867 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5027. Min Range: -3.5027
Max Act: 3.2832. Min Act: -0.1700
Data Index: 4145905 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5027. Min Range: -3.5027
Max Act: 3.2675. Min Act: -0.1700
Data Index: 7529626 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5027. Min Range: -3.5027
Max Act: 3.2517. Min Act: -0.1700
Data Index: 3154078 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5027. Min Range: -3.5027
Max Act: 3.2517. Min Act: -0.1700
Data Index: 3955774 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5027. Min Range: -3.5027
Max Act: 3.2360. Min Act: -0.1700
Data Index: 1108890 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5027. Min Range: -3.5027
Max Act: 3.2046. Min Act: -0.1700
Data Index: 3700973 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5027. Min Range: -3.5027
Max Act: 3.1889. Min Act: -0.1700
Data Index: 6048289 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5027. Min Range: -3.5027
Max Act: 3.2046. Min Act: -0.1700
Data Index: 432883 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5027. Min Range: -3.5027
Max Act: 3.1889. Min Act: -0.1700
Data Index: 6215762 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5027. Min Range: -3.5027
Max Act: 3.2046. Min Act: -0.1700
Data Index: 7948972 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5027. Min Range: -3.5027
Max Act: 3.1574. Min Act: -0.1700
Data Index: 4630703 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5027. Min Range: -3.5027
Max Act: 3.1889. Min Act: -0.1700
Data Index: 540770 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5027. Min Range: -3.5027
Max Act: 3.1417. Min Act: -0.1700
Data Index: 8822619 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5027. Min Range: -3.5027
Max Act: 3.1731. Min Act: -0.1700
Data Index: 7237816 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5027. Min Range: -3.5027
Max Act: 3.1574. Min Act: -0.1700
Data Index: 1876827 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #19