Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4160 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4329. Min Range: -3.4329
Max Act: 3.4329. Min Act: -0.1700
Data Index: 6061132 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4329. Min Range: -3.4329
Max Act: 3.1188. Min Act: -0.1700
Data Index: 7444692 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4329. Min Range: -3.4329
Max Act: 3.1030. Min Act: -0.1700
Data Index: 7414876 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4329. Min Range: -3.4329
Max Act: 3.0872. Min Act: -0.1700
Data Index: 1768547 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4329. Min Range: -3.4329
Max Act: 3.0557. Min Act: -0.1700
Data Index: 7604877 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4329. Min Range: -3.4329
Max Act: 3.0557. Min Act: -0.1700
Data Index: 834720 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4329. Min Range: -3.4329
Max Act: 3.0715. Min Act: -0.1700
Data Index: 7193523 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4329. Min Range: -3.4329
Max Act: 3.0241. Min Act: -0.1700
Data Index: 3322384 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4329. Min Range: -3.4329
Max Act: 3.0083. Min Act: -0.1700
Data Index: 4058886 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4329. Min Range: -3.4329
Max Act: 3.0083. Min Act: -0.1700
Data Index: 2249441 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4329. Min Range: -3.4329
Max Act: 3.0083. Min Act: -0.1700
Data Index: 2566512 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4329. Min Range: -3.4329
Max Act: 3.0083. Min Act: -0.1700
Data Index: 6456961 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4329. Min Range: -3.4329
Max Act: 3.0083. Min Act: -0.1700
Data Index: 1135652 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4329. Min Range: -3.4329
Max Act: 2.9925. Min Act: -0.1700
Data Index: 4129647 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4329. Min Range: -3.4329
Max Act: 2.9767. Min Act: -0.1700
Data Index: 7784202 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4329. Min Range: -3.4329
Max Act: 2.9609. Min Act: -0.1700
Data Index: 6132109 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4329. Min Range: -3.4329
Max Act: 2.9767. Min Act: -0.1700
Data Index: 1410258 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4329. Min Range: -3.4329
Max Act: 2.9609. Min Act: -0.1700
Data Index: 649752 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4329. Min Range: -3.4329
Max Act: 2.9767. Min Act: -0.1700
Data Index: 4504892 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4329. Min Range: -3.4329
Max Act: 2.9451. Min Act: -0.1700
Data Index: 6408337 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #19