Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2529 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7906. Min Range: -4.7906
Max Act: 4.7906. Min Act: -0.1700
Data Index: 6086509 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7906. Min Range: -4.7906
Max Act: 4.7281. Min Act: -0.1700
Data Index: 174057 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7906. Min Range: -4.7906
Max Act: 4.6969. Min Act: -0.1700
Data Index: 5426012 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7906. Min Range: -4.7906
Max Act: 4.6656. Min Act: -0.1700
Data Index: 1494706 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7906. Min Range: -4.7906
Max Act: 4.5719. Min Act: -0.1700
Data Index: 2858844 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7906. Min Range: -4.7906
Max Act: 4.5406. Min Act: -0.1700
Data Index: 1888602 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7906. Min Range: -4.7906
Max Act: 4.5719. Min Act: -0.1700
Data Index: 6259165 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7906. Min Range: -4.7906
Max Act: 4.5719. Min Act: -0.1700
Data Index: 1131892 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7906. Min Range: -4.7906
Max Act: 4.5719. Min Act: -0.1700
Data Index: 6998318 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7906. Min Range: -4.7906
Max Act: 4.6031. Min Act: -0.1700
Data Index: 4445349 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7906. Min Range: -4.7906
Max Act: 4.5406. Min Act: -0.1700
Data Index: 3952294 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7906. Min Range: -4.7906
Max Act: 4.5406. Min Act: -0.1700
Data Index: 5566252 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7906. Min Range: -4.7906
Max Act: 4.5406. Min Act: -0.1700
Data Index: 428833 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7906. Min Range: -4.7906
Max Act: 4.5719. Min Act: -0.1700
Data Index: 3171386 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7906. Min Range: -4.7906
Max Act: 4.5094. Min Act: -0.1700
Data Index: 186961 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7906. Min Range: -4.7906
Max Act: 4.5406. Min Act: -0.1700
Data Index: 7590760 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7906. Min Range: -4.7906
Max Act: 4.5094. Min Act: -0.1700
Data Index: 3297224 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7906. Min Range: -4.7906
Max Act: 4.5406. Min Act: -0.1700
Data Index: 6675741 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7906. Min Range: -4.7906
Max Act: 4.5406. Min Act: -0.1700
Data Index: 1844011 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7906. Min Range: -4.7906
Max Act: 4.5094. Min Act: -0.1700
Data Index: 406563 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #19