Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2133 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6992. Min Range: -4.6992
Max Act: 4.6992. Min Act: -0.1700
Data Index: 7027023 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6992. Min Range: -4.6992
Max Act: 4.2617. Min Act: -0.1700
Data Index: 6677806 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6992. Min Range: -4.6992
Max Act: 4.1367. Min Act: -0.1700
Data Index: 6410197 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6992. Min Range: -4.6992
Max Act: 4.0742. Min Act: -0.1700
Data Index: 1554801 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6992. Min Range: -4.6992
Max Act: 4.1054. Min Act: -0.1700
Data Index: 6857708 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6992. Min Range: -4.6992
Max Act: 4.0429. Min Act: -0.1700
Data Index: 4150594 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6992. Min Range: -4.6992
Max Act: 3.9335. Min Act: -0.1700
Data Index: 4245565 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6992. Min Range: -4.6992
Max Act: 3.9648. Min Act: -0.1700
Data Index: 2158373 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6992. Min Range: -4.6992
Max Act: 3.9491. Min Act: -0.1700
Data Index: 2228848 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6992. Min Range: -4.6992
Max Act: 3.9491. Min Act: -0.1700
Data Index: 6748976 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6992. Min Range: -4.6992
Max Act: 3.9335. Min Act: -0.1700
Data Index: 271331 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6992. Min Range: -4.6992
Max Act: 3.9491. Min Act: -0.1700
Data Index: 2299372 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6992. Min Range: -4.6992
Max Act: 3.9179. Min Act: -0.1700
Data Index: 2956559 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6992. Min Range: -4.6992
Max Act: 3.9179. Min Act: -0.1700
Data Index: 1152745 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6992. Min Range: -4.6992
Max Act: 3.9335. Min Act: -0.1700
Data Index: 1787798 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6992. Min Range: -4.6992
Max Act: 3.9335. Min Act: -0.1700
Data Index: 6891661 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6992. Min Range: -4.6992
Max Act: 3.8866. Min Act: -0.1700
Data Index: 6867011 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6992. Min Range: -4.6992
Max Act: 3.8710. Min Act: -0.1700
Data Index: 1067485 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6992. Min Range: -4.6992
Max Act: 3.8866. Min Act: -0.1700
Data Index: 7999020 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6992. Min Range: -4.6992
Max Act: 3.8710. Min Act: -0.1700
Data Index: 3902761 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19