Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3863 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9210. Min Range: -4.9210
Max Act: 4.9210. Min Act: -0.1700
Data Index: 4102057 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9210. Min Range: -4.9210
Max Act: 4.9210. Min Act: -0.1700
Data Index: 4752168 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9210. Min Range: -4.9210
Max Act: 4.9210. Min Act: -0.1700
Data Index: 2707039 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9210. Min Range: -4.9210
Max Act: 4.7648. Min Act: -0.1700
Data Index: 1583788 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9210. Min Range: -4.9210
Max Act: 4.7648. Min Act: -0.1700
Data Index: 362835 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9210. Min Range: -4.9210
Max Act: 4.7335. Min Act: -0.1700
Data Index: 1974592 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9210. Min Range: -4.9210
Max Act: 4.7335. Min Act: -0.1700
Data Index: 1341100 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9210. Min Range: -4.9210
Max Act: 4.7023. Min Act: -0.1700
Data Index: 7938815 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9210. Min Range: -4.9210
Max Act: 4.7023. Min Act: -0.1700
Data Index: 5683255 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9210. Min Range: -4.9210
Max Act: 4.6710. Min Act: -0.1700
Data Index: 4399562 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9210. Min Range: -4.9210
Max Act: 4.5773. Min Act: -0.1700
Data Index: 1830719 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9210. Min Range: -4.9210
Max Act: 4.5148. Min Act: -0.1700
Data Index: 5096067 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9210. Min Range: -4.9210
Max Act: 4.5773. Min Act: -0.1700
Data Index: 7744539 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9210. Min Range: -4.9210
Max Act: 4.5460. Min Act: -0.1700
Data Index: 5038587 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9210. Min Range: -4.9210
Max Act: 4.5460. Min Act: -0.1700
Data Index: 8824295 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9210. Min Range: -4.9210
Max Act: 4.5460. Min Act: -0.1700
Data Index: 2377193 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9210. Min Range: -4.9210
Max Act: 4.5148. Min Act: -0.1700
Data Index: 2186965 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9210. Min Range: -4.9210
Max Act: 4.5148. Min Act: -0.1700
Data Index: 7124285 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9210. Min Range: -4.9210
Max Act: 4.5148. Min Act: -0.1700
Data Index: 5999190 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9210. Min Range: -4.9210
Max Act: 4.5148. Min Act: -0.1700
Data Index: 5121375 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19