Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4086 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7117. Min Range: -5.7117
Max Act: 5.7117. Min Act: -0.1700
Data Index: 2662132 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7117. Min Range: -5.7117
Max Act: 5.6492. Min Act: -0.1700
Data Index: 1867054 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7117. Min Range: -5.7117
Max Act: 5.6492. Min Act: -0.1700
Data Index: 8785815 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7117. Min Range: -5.7117
Max Act: 5.5554. Min Act: -0.1700
Data Index: 3109305 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7117. Min Range: -5.7117
Max Act: 5.4929. Min Act: -0.1700
Data Index: 5771572 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7117. Min Range: -5.7117
Max Act: 5.3992. Min Act: -0.1700
Data Index: 4050900 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7117. Min Range: -5.7117
Max Act: 5.3992. Min Act: -0.1700
Data Index: 3581074 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7117. Min Range: -5.7117
Max Act: 5.3367. Min Act: -0.1700
Data Index: 2104184 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7117. Min Range: -5.7117
Max Act: 5.3367. Min Act: -0.1700
Data Index: 8802261 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7117. Min Range: -5.7117
Max Act: 5.3367. Min Act: -0.1700
Data Index: 8440955 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7117. Min Range: -5.7117
Max Act: 5.3367. Min Act: -0.1700
Data Index: 8031859 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7117. Min Range: -5.7117
Max Act: 5.2742. Min Act: -0.1700
Data Index: 639128 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7117. Min Range: -5.7117
Max Act: 5.3054. Min Act: -0.1700
Data Index: 8440959 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7117. Min Range: -5.7117
Max Act: 5.3054. Min Act: -0.1700
Data Index: 5543433 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7117. Min Range: -5.7117
Max Act: 5.2429. Min Act: -0.1700
Data Index: 8674366 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7117. Min Range: -5.7117
Max Act: 5.2742. Min Act: -0.1700
Data Index: 92246 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7117. Min Range: -5.7117
Max Act: 5.2429. Min Act: -0.1700
Data Index: 3109306 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7117. Min Range: -5.7117
Max Act: 5.1804. Min Act: -0.1700
Data Index: 2104182 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7117. Min Range: -5.7117
Max Act: 5.2117. Min Act: -0.1700
Data Index: 2530906 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7117. Min Range: -5.7117
Max Act: 5.1804. Min Act: -0.1700
Data Index: 1356713 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19