Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1097 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6594. Min Range: -5.6594
Max Act: 5.6594. Min Act: -0.1700
Data Index: 3970079 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6594. Min Range: -5.6594
Max Act: 5.6281. Min Act: -0.1700
Data Index: 7338336 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6594. Min Range: -5.6594
Max Act: 5.6281. Min Act: -0.1700
Data Index: 8188455 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6594. Min Range: -5.6594
Max Act: 5.5969. Min Act: -0.1700
Data Index: 5206974 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6594. Min Range: -5.6594
Max Act: 5.5656. Min Act: -0.1700
Data Index: 3321804 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6594. Min Range: -5.6594
Max Act: 5.5344. Min Act: -0.1700
Data Index: 8608508 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6594. Min Range: -5.6594
Max Act: 5.5656. Min Act: -0.1700
Data Index: 4405475 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6594. Min Range: -5.6594
Max Act: 5.5969. Min Act: -0.1700
Data Index: 6096942 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6594. Min Range: -5.6594
Max Act: 5.5344. Min Act: -0.1700
Data Index: 7594521 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6594. Min Range: -5.6594
Max Act: 5.5344. Min Act: -0.1700
Data Index: 791300 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6594. Min Range: -5.6594
Max Act: 5.5031. Min Act: -0.1700
Data Index: 6567703 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6594. Min Range: -5.6594
Max Act: 5.4719. Min Act: -0.1700
Data Index: 2427673 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6594. Min Range: -5.6594
Max Act: 5.4719. Min Act: -0.1700
Data Index: 906749 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6594. Min Range: -5.6594
Max Act: 5.4094. Min Act: -0.1700
Data Index: 4850661 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6594. Min Range: -5.6594
Max Act: 5.4406. Min Act: -0.1700
Data Index: 2158589 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6594. Min Range: -5.6594
Max Act: 5.4406. Min Act: -0.1700
Data Index: 8745361 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6594. Min Range: -5.6594
Max Act: 5.4406. Min Act: -0.1700
Data Index: 1157130 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6594. Min Range: -5.6594
Max Act: 5.4406. Min Act: -0.1700
Data Index: 7920721 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6594. Min Range: -5.6594
Max Act: 5.4406. Min Act: -0.1700
Data Index: 5160375 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6594. Min Range: -5.6594
Max Act: 5.3781. Min Act: -0.1700
Data Index: 6256391 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19