Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2834 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8899. Min Range: -2.8899
Max Act: 2.8899. Min Act: -0.1700
Data Index: 4679957 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8899. Min Range: -2.8899
Max Act: 2.8581. Min Act: -0.1700
Data Index: 1620112 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8899. Min Range: -2.8899
Max Act: 2.7467. Min Act: -0.1700
Data Index: 6289419 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8899. Min Range: -2.8899
Max Act: 2.7467. Min Act: -0.1700
Data Index: 6089349 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8899. Min Range: -2.8899
Max Act: 2.7307. Min Act: -0.1700
Data Index: 839209 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8899. Min Range: -2.8899
Max Act: 2.7307. Min Act: -0.1700
Data Index: 4078785 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8899. Min Range: -2.8899
Max Act: 2.6987. Min Act: -0.1700
Data Index: 8566947 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8899. Min Range: -2.8899
Max Act: 2.6987. Min Act: -0.1700
Data Index: 4838910 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8899. Min Range: -2.8899
Max Act: 2.6827. Min Act: -0.1700
Data Index: 6430044 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8899. Min Range: -2.8899
Max Act: 2.6827. Min Act: -0.1700
Data Index: 6256496 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8899. Min Range: -2.8899
Max Act: 2.6827. Min Act: -0.1700
Data Index: 831779 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8899. Min Range: -2.8899
Max Act: 2.6827. Min Act: -0.1700
Data Index: 6735280 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8899. Min Range: -2.8899
Max Act: 2.6507. Min Act: -0.1700
Data Index: 1201696 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8899. Min Range: -2.8899
Max Act: 2.6507. Min Act: -0.1700
Data Index: 1778857 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8899. Min Range: -2.8899
Max Act: 2.6827. Min Act: -0.1700
Data Index: 3580927 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8899. Min Range: -2.8899
Max Act: 2.6507. Min Act: -0.1700
Data Index: 571258 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8899. Min Range: -2.8899
Max Act: 2.6667. Min Act: -0.1700
Data Index: 3339853 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8899. Min Range: -2.8899
Max Act: 2.6346. Min Act: -0.1700
Data Index: 1391655 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8899. Min Range: -2.8899
Max Act: 2.6827. Min Act: -0.1700
Data Index: 1180176 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8899. Min Range: -2.8899
Max Act: 2.6185. Min Act: -0.1700
Data Index: 3046710 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #19